Thoughts on AI, technology, and the future we're building.
New posts every week
A sortable view of frontier model performance across public Arena evals, with space for independent intelligence, cost, and coding benchmarks as the data layer expands.
Models tracked
Arena views
Labs covered
SWE-bench matches
Current leader
Text Arena
Code Arena
Vision Arena
SWE-bench
201 models shown
Arena and SWE-bench scores are higher-is-better. Latency and price are lower-is-better.
claude-opus-4-6-thinking
claude-opus-4-7-thinking
claude-opus-4-6
claude-opus-4-7
muse-spark
gemini-3.1-pro-preview
gemini-3-pro
gpt-5.5-high
gpt-5.4-high
gemini-3.5-flash
gpt-5.5
gpt-5.2-chat-latest-20260210
grok-4.20-beta1
grok-4.20-beta-0309-reasoning
qwen3.7-max-preview
glm-5.1
gpt-5.5-instant
claude-opus-4-5-20251101-thinking-32k
grok-4.20-multi-agent-beta-0309
ernie-5.1
claude-sonnet-4-6
gpt-5.4
claude-opus-4-5-20251101
grok-4.1-thinking
qwen3.5-max-preview
mimo-v2.5-pro
kimi-k2.6
gemini-3-flash (thinking-minimal)
grok-4.1
qwen3.6-max-preview
deepseek-v4-pro-thinking
glm-5
dola-seed-2.0-pro
claude-sonnet-4-5-20250929
claude-sonnet-4-5-20250929-thinking-32k
gpt-5.1-high
deepseek-v4-pro
gemma-4-31b
gpt-5.4-mini-high
kimi-k2.5-thinking
ernie-5.0-preview-1203
claude-opus-4-1-20250805-thinking-16k
gpt-5.3-chat-latest
mimo-v2-pro
ernie-5.0-0110
claude-opus-4-1-20250805
grok-4.3
gemini-2.5-pro
qwen3.5-397b-a17b
gpt-4.5-preview-2025-02-27
qwen3.6-plus
chatgpt-4o-latest-20250326
glm-4.7
gpt-5.1
gemma-4-26b-a4b
gpt-5.2-high
deepseek-v4-flash-thinking
longcat-flash-chat-2602-exp
qwen3-max-preview
gpt-5.2
mimo-v2.5
gpt-5-high
gemini-3.1-flash-lite-preview
deepseek-v4-flash
kimi-k2.5-instant
o3-2025-04-16
grok-4-1-fast-reasoning
kimi-k2-thinking-turbo
amazon-nova-experimental-chat-26-02-10
gpt-5-chat
glm-4.6
deepseek-v3.2-exp-thinking
deepseek-v3.2
claude-opus-4-20250514-thinking-16k
qwen3-max-2025-09-23
deepseek-v3.2-exp
qwen3-235b-a22b-instruct-2507
deepseek-r1-0528
deepseek-v3.2-thinking
grok-4-fast-chat
ernie-5.0-preview-1022
kimi-k2-0905-preview
deepseek-v3.1
deepseek-v3.1-terminus-thinking
kimi-k2-0711-preview
qwen3.5-122b-a10b
deepseek-v3.1-thinking
deepseek-v3.1-terminus
amazon-nova-experimental-chat-26-01-10
hunyuan-hy3-preview
qwen3-vl-235b-a22b-instruct
mistral-large-3
mimo-v2-omni
gpt-4.1-2025-04-14
minimax-m2.7
claude-opus-4-20250514
grok-3-preview-02-24
glm-4.5
gemini-2.5-flash
api-gpt-4o-search
claude-3-5-haiku-20241022
claude-3-5-sonnet-20240620
claude-3-5-sonnet-20241022
claude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219-thinking-32k
claude-haiku-4-5-20251001
claude-opus-4-search
claude-opus-4-1-search
claude-opus-4-5-search
claude-opus-4-6-search
claude-sonnet-4-20250514
claude-sonnet-4-20250514-thinking-32k
claude-sonnet-4-5-search
claude-sonnet-4-6-search
devstral-2
devstral-medium-2507
diffbot-small-xl
ernie-5.0-preview-1220
gemini-1.5-flash-002
gemini-1.5-pro-001
gemini-1.5-pro-002
gemini-2.0-flash-001
gemini-2.0-flash-lite-preview-02-05
gemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-preview-09-2025
gemini-2.5-pro-grounding
gemini-3-flash-grounding
gemini-3-pro-grounding
gemini-3.1-pro-grounding
gemma-3-27b-it
glm-4.5v
glm-4.6v
glm-5v-turbo
gpt-4o-2024-05-13
gpt-4o-2024-08-06
gpt-4o-mini-2024-07-18
gpt-4-turbo-2024-04-09
gpt-4.1-mini-2025-04-14
gpt-4.1-nano-2025-04-14
gpt-5-medium
gpt-5-mini-high
gpt-5-nano-high
gpt-5-search
gpt-5.1-codex
gpt-5.1-codex-mini
gpt-5.1-medium
gpt-5.1-search
gpt-5.2-codex
gpt-5.2-search
gpt-5.2-search-non-reasoning
gpt-5.3-codex (codex-harness)
gpt-5.4-medium (codex-harness)
gpt-5.4-nano-high
gpt-5.4-search
gpt-5.5-search
gpt-5.5-xhigh (codex-harness)
granite-4.1-8b
grok-4-0709
grok-4-fast-reasoning
grok-4-fast-search
grok-4-search
grok-4-1-fast-search
grok-code-fast-1
hunyuan-large-vision
hunyuan-vision-1.5-thinking
KAT-Coder-Pro-V1
llama-4-maverick-17b-128e-instruct
llama-4-scout-17b-16e-instruct
mercury-2
mimo-v2-flash (non-thinking)
minimax-m2
minimax-m2.1-preview
minimax-m2.5
mistral-medium-2505
mistral-medium-2508
mistral-small-2506
mistral-small-3.1-24b-instruct-2503
molmo-2-8b
o1-2024-12-17
o3-search
o4-mini-2025-04-16
pixtral-large-2411
ppl-sonar-pro-high
ppl-sonar-reasoning-pro-high
qwen-vl-max-1119
qwen-vl-max-2025-08-13
qwen2-vl-72b
qwen2.5-vl-32b-instruct
qwen2.5-vl-72b-instruct
qwen3-coder-480b-a35b-instruct
qwen3-vl-235b-a22b-thinking
qwen3.5-27b
qwen3.5-35b-a3b
qwen3.5-flash
qwen3.7-max-20260517
qwen3.7-plus-preview
step-1o-turbo-202506
step-1o-vision-32k-highres
step-3
trinity-large-thinking
| Model info | Arena benchmarks | Cost and speed | Coding eval | Freshness | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Rank | Latest | ||||||||||||
| #1 | Claude Opus 4.6 Thinking claude-opus-4-6-thinking FrontierReasoning+2 | Anthropic | Proprietary | 1502#1 1498-1506 CI 34,186 votes | 1542#3 1534-1550 CI 7,919 votes | 1300#3 1291-1309 CI 7,135 votes | Not listed | Not listed | $10.94 blended / 1M $6.25 in / $25.00 out | 11.2s time to first token Artificial Analysis | 48 output tok/sec median | Not listed | May 27, 2026 |
| #2 | Claude Opus 4.7 Thinking claude-opus-4-7-thinking FrontierReasoning+2 | Anthropic | Proprietary | 1500#2 1494-1505 CI 19,973 votes | 1567#1 1557-1576 CI 5,270 votes | 1306#1 1297-1315 CI 6,531 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #3 | Claude Opus 4.6 claude-opus-4-6 FrontierCoding+1 | Anthropic | Proprietary | 1498#3 1494-1503 CI 36,512 votes | 1538#5 1531-1546 CI 8,889 votes | 1293#5 1285-1301 CI 8,549 votes | Not listed | Not listed | $10.94 blended / 1M $6.25 in / $25.00 out | 1.46s time to first token Artificial Analysis | 43 output tok/sec median | 75.6%#4 bash-only mini 2.0.0 | May 27, 2026 |
| #4 | Claude Opus 4.7 claude-opus-4-7 FrontierCoding+1 | Anthropic | Proprietary | 1494#4 1488-1499 CI 20,724 votes | 1562#2 1553-1572 CI 4,862 votes | 1304#2 1295-1313 CI 6,779 votes | 1214#3 1206-1222 CI 9,696 votes | Not listed | $10.94 blended / 1M $6.25 in / $25.00 out | 1.14s time to first token Artificial Analysis | 42 output tok/sec median | Not listed | May 27, 2026 |
| #5 | Muse Spark muse-spark FrontierCoding+1 | Meta | Proprietary | 1489#5 1483-1495 CI 12,228 votes | 1508#9 1492-1524 CI 1,627 votes | 1296#4 1286-1306 CI 4,526 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #6 | Gemini 3.1 Pro Preview gemini-3.1-pro-preview FrontierCoding+1 | Proprietary | 1487#6 1483-1492 CI 43,742 votes | 1448#20 1442-1455 CI 10,289 votes | 1277#10 1271-1284 CI 16,807 votes | Not listed | Not listed | $4.50 blended / 1M $2.00 in / $12.00 out | 22.5s time to first token Artificial Analysis | 120 output tok/sec median | Not listed | May 27, 2026 | |
| #7 | Gemini 3 Pro gemini-3-pro FrontierMultimodal | Proprietary | 1486#7 1482-1490 CI 41,332 votes | 1438#24 1431-1446 CI 17,155 votes | 1289#6 1281-1297 CI 13,226 votes | Not listed | Not listed | $4.50 blended / 1M $2.00 in / $12.00 out | Not listed | Not listed | 74.2%#6 bash-only mini 1.15.0 | May 27, 2026 | |
| #8 | GPT-5.5 High gpt-5.5-high FrontierReasoning+2 | OpenAI | Proprietary | 1482#8 1477-1488 CI 16,573 votes | 1479#14 1469-1489 CI 4,348 votes | 1278#9 1268-1289 CI 4,238 votes | Not listed | Not listed | $11.25 blended / 1M $5.00 in / $30.00 out | 17.1s time to first token Artificial Analysis | 61 output tok/sec median | Not listed | May 27, 2026 |
| #9 | GPT-5.4 High gpt-5.4-high FrontierReasoning+2 | OpenAI | Proprietary | 1480#9 1476-1485 CI 28,246 votes | 1457#19 1440-1474 CI 1,483 votes | 1277#11 1267-1286 CI 5,884 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #10 | Gemini 3.5 Flash gemini-3.5-flash FrontierCoding | Proprietary | 1479#10 1472-1486 CI 9,045 votes | 1506#10 1493-1520 CI 2,213 votes | Not listed | Not listed | Not listed | $3.38 blended / 1M $1.50 in / $9.00 out | 12.4s time to first token Artificial Analysis | 198 output tok/sec median | Not listed | May 27, 2026 | |
| #11 | GPT-5.5 gpt-5.5 FrontierMultimodal | OpenAI | Proprietary | 1476#11 1471-1482 CI 16,852 votes | 1444#21 1434-1454 CI 4,145 votes | 1288#7 1277-1298 CI 4,662 votes | Not listed | Not listed | $11.25 blended / 1M $5.00 in / $30.00 out | 0.90s time to first token Artificial Analysis | 51 output tok/sec median | Not listed | May 27, 2026 |
| #12 | GPT-5.2 Chat Latest 20260210 gpt-5.2-chat-latest-20260210 FrontierMultimodal | OpenAI | Proprietary | 1476#12 1472-1481 CI 32,280 votes | Not listed | 1280#8 1273-1288 CI 12,478 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #13 | Grok 4.20 Beta 1 grok-4.20-beta1 Frontier | xAI | Proprietary | 1476#13 1471-1481 CI 24,468 votes | Not listed | Not listed | 1199#8 1192-1205 CI 48,961 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #14 | Grok 4.20 Beta 0309 Reasoning grok-4.20-beta-0309-reasoning FrontierReasoning | xAI | Proprietary | 1475#14 1471-1480 CI 29,068 votes | 1395#35 1387-1403 CI 7,216 votes | 1251#21 1243-1259 CI 9,550 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #15 | Qwen3.7 Max Preview qwen3.7-max-preview Frontier | Alibaba | Proprietary | 1475#15 1465-1485 CI 3,755 votes | Not listed | Not listed | Not listed | Not listed | $3.75 blended / 1M $2.50 in / $7.50 out | 1.75s time to first token Artificial Analysis | 186 output tok/sec median | Not listed | May 27, 2026 |
| #16 | GLM 5.1 glm-5.1 FrontierOpen weights+1 | Z.ai | Open weights | 1474#16 1468-1480 CI 13,957 votes | 1533#6 1522-1544 CI 3,611 votes | Not listed | Not listed | Not listed | $2.15 blended / 1M $1.40 in / $4.40 out | 1.10s time to first token Artificial Analysis | 49 output tok/sec median | Not listed | May 27, 2026 |
| #17 | GPT-5.5 Instant gpt-5.5-instant FrontierMultimodal | OpenAI | Proprietary | 1474#17 1469-1479 CI 24,925 votes | Not listed | 1275#13 1263-1286 CI 3,645 votes | Not listed | Not listed | $11.25 blended / 1M $5.00 in / $30.00 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #18 | Claude Opus 4.5 20251101 Thinking 32K claude-opus-4-5-20251101-thinking-32k FrontierReasoning+1 | Anthropic | Proprietary | 1473#19 1469-1476 CI 37,130 votes | 1490#12 1483-1498 CI 13,063 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #19 | Grok 4.20 Multi Agent Beta 0309 grok-4.20-multi-agent-beta-0309 Frontier | xAI | Proprietary | 1472#20 1468-1477 CI 28,630 votes | Not listed | 1247#26 1239-1255 CI 8,881 votes | 1211#5 1205-1218 CI 27,452 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #20 | ERNIE 5.1 ernie-5.1 Frontier | Baidu | Proprietary | 1470#21 1465-1476 CI 14,675 votes | Not listed | Not listed | 1193#13 1181-1205 CI 2,293 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #21 | Claude Sonnet 4.6 claude-sonnet-4-6 FrontierCoding+1 | Anthropic | Proprietary | 1470#22 1465-1474 CI 27,474 votes | 1523#7 1516-1530 CI 11,120 votes | 1275#12 1267-1283 CI 8,916 votes | Not listed | Not listed | $6.56 blended / 1M $3.75 in / $15.00 out | 1.14s time to first token Artificial Analysis | 47 output tok/sec median | Not listed | May 27, 2026 |
| #22 | GPT-5.4 gpt-5.4 FrontierMultimodal | OpenAI | Proprietary | 1469#23 1465-1474 CI 29,672 votes | 1388#40 1350-1427 CI 239 votes | 1269#15 1260-1279 CI 5,580 votes | Not listed | Not listed | $5.63 blended / 1M $2.50 in / $15.00 out | 198.5s time to first token Artificial Analysis | 78 output tok/sec median | Not listed | May 27, 2026 |
| #23 | Claude Opus 4.5 20251101 claude-opus-4-5-20251101 FrontierCoding | Anthropic | Proprietary | 1469#24 1466-1472 CI 66,107 votes | 1467#16 1461-1473 CI 15,300 votes | Not listed | Not listed | Not listed | $10.94 blended / 1M $6.25 in / $25.00 out | 12.0s time to first token Artificial Analysis | 54 output tok/sec median | 76.8%#1 bash-only mini 2.0.0 | May 27, 2026 |
| #24 | Grok 4.1 Thinking grok-4.1-thinking FrontierReasoning | xAI | Proprietary | 1466#25 1463-1470 CI 63,569 votes | 1209#74 1189-1228 CI 1,209 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #25 | Qwen3.5 Max Preview qwen3.5-max-preview | Alibaba | Proprietary | 1466#26 1460-1471 CI 20,212 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #26 | MiMo V2.5 Pro mimo-v2.5-pro Open weightsCoding | Xiaomi | Open weights | 1465#27 1459-1470 CI 15,722 votes | 1471#15 1462-1481 CI 4,719 votes | Not listed | Not listed | Not listed | $1.35 blended / 1M $0.900 in / $2.70 out | 2.49s time to first token Artificial Analysis | 46 output tok/sec median | Not listed | May 27, 2026 |
| #27 | Kimi K2.6 kimi-k2.6 Open weightsCoding+1 | Moonshot AI | Open weights | 1462#28 1457-1468 CI 15,765 votes | 1518#8 1508-1528 CI 4,008 votes | 1259#19 1250-1269 CI 5,612 votes | Not listed | Not listed | $1.71 blended / 1M $0.950 in / $4.00 out | 1.33s time to first token Artificial Analysis | 39 output tok/sec median | Not listed | May 27, 2026 |
| #28 | Gemini 3 Flash gemini-3-flash (thinking-minimal) ReasoningMultimodal | Proprietary | 1461#29 1458-1465 CI 52,876 votes | 1387#42 1381-1393 CI 16,396 votes | 1260#17 1253-1267 CI 19,319 votes | Not listed | Not listed | $1.13 blended / 1M $0.500 in / $3.00 out | 0.94s time to first token Artificial Analysis | 184 output tok/sec median | 75.8%#2 bash-only mini 2.0.0 | May 27, 2026 | |
| #29 | Grok 4.1 grok-4.1 | xAI | Proprietary | 1460#30 1457-1463 CI 65,655 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #30 | Qwen3.6 Max Preview qwen3.6-max-preview Coding | Alibaba | Proprietary | 1459#31 1450-1468 CI 4,648 votes | 1486#13 1473-1498 CI 2,498 votes | Not listed | Not listed | Not listed | $2.93 blended / 1M $1.30 in / $7.80 out | 1.89s time to first token Artificial Analysis | 41 output tok/sec median | Not listed | May 27, 2026 |
| #31 | DeepSeek V4 Pro Thinking deepseek-v4-pro-thinking ReasoningOpen weights+1 | DeepSeek | Open weights | 1458#32 1452-1463 CI 15,852 votes | 1464#17 1453-1474 CI 3,956 votes | Not listed | Not listed | Not listed | $0.544 blended / 1M $0.435 in / $0.870 out | 1.07s time to first token Artificial Analysis | 45 output tok/sec median | Not listed | May 27, 2026 |
| #32 | GLM 5 glm-5 Open weights | Z.ai | Open weights | 1457#33 1452-1462 CI 21,930 votes | 1436#27 1427-1444 CI 6,574 votes | Not listed | Not listed | Not listed | $1.55 blended / 1M $1.00 in / $3.20 out | 0.80s time to first token Artificial Analysis | 81 output tok/sec median | 72.8%#8 bash-only mini 2.0.0 | May 27, 2026 |
| #33 | Dola Seed 2.0 Pro dola-seed-2.0-pro Multimodal | ByteDance | Proprietary | 1456#34 1452-1460 CI 37,742 votes | Not listed | 1259#18 1251-1268 CI 8,926 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #34 | Claude Sonnet 4.5 20250929 claude-sonnet-4-5-20250929 | Anthropic | Proprietary | 1455#35 1452-1458 CI 76,121 votes | 1386#43 1380-1392 CI 18,386 votes | Not listed | Not listed | Not listed | $6.56 blended / 1M $3.75 in / $15.00 out | 1.38s time to first token Artificial Analysis | 43 output tok/sec median | 71.4%#12 bash-only mini 2.0.0 | May 27, 2026 |
| #35 | Claude Sonnet 4.5 20250929 Thinking 32K claude-sonnet-4-5-20250929-thinking-32k Reasoning | Anthropic | Proprietary | 1455#36 1452-1458 CI 77,813 votes | 1388#41 1382-1395 CI 15,739 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #36 | GPT-5.1 High gpt-5.1-high Reasoning | OpenAI | Proprietary | 1455#37 1451-1459 CI 40,856 votes | Not listed | 1250#22 1242-1259 CI 9,240 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #37 | DeepSeek V4 Pro deepseek-v4-pro Open weights | DeepSeek | Open weights | 1454#38 1449-1460 CI 16,920 votes | Not listed | Not listed | Not listed | Not listed | $0.544 blended / 1M $0.435 in / $0.870 out | 1.15s time to first token Artificial Analysis | 45 output tok/sec median | Not listed | May 27, 2026 |
| #38 | Gemma 4 31b gemma-4-31b Open weights | Open weights | 1452#39 1444-1460 CI 5,855 votes | 1380#46 1369-1390 CI 3,380 votes | 1248#23 1241-1255 CI 17,337 votes | Not listed | Not listed | Not listed | 0.97s time to first token Artificial Analysis | 35 output tok/sec median | Not listed | May 27, 2026 | |
| #39 | GPT-5.4 Mini High gpt-5.4-mini-high ReasoningMultimodal | OpenAI | Proprietary | 1451#40 1447-1456 CI 26,397 votes | 1402#33 1393-1411 CI 5,497 votes | 1254#20 1246-1262 CI 8,582 votes | Not listed | Not listed | $1.69 blended / 1M $0.750 in / $4.50 out | 7.68s time to first token Artificial Analysis | 165 output tok/sec median | Not listed | May 27, 2026 |
| #40 | Kimi K2.5 Thinking kimi-k2.5-thinking ReasoningOpen weights | Moonshot AI | Open weights | 1449#41 1445-1453 CI 36,795 votes | 1431#29 1424-1437 CI 10,684 votes | 1247#24 1240-1254 CI 14,366 votes | Not listed | Not listed | $1.19 blended / 1M $0.580 in / $3.00 out | 1.38s time to first token Artificial Analysis | 33 output tok/sec median | 70.8%#13 bash-only mini 2.0.0 | May 27, 2026 |
| #41 | ERNIE 5.0 Preview 1203 ernie-5.0-preview-1203 | Baidu | Proprietary | 1449#42 1443-1456 CI 9,752 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #42 | Claude Opus 4.1 20250805 Thinking 16K claude-opus-4-1-20250805-thinking-16k Reasoning | Anthropic | Proprietary | 1449#43 1446-1452 CI 49,833 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #43 | GPT-5.3 Chat Latest gpt-5.3-chat-latest | OpenAI | Proprietary | 1449#44 1444-1453 CI 30,882 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #44 | MiMo V2 Pro mimo-v2-pro | Xiaomi | Proprietary | 1448#45 1443-1453 CI 22,638 votes | 1434#28 1426-1442 CI 6,784 votes | Not listed | Not listed | Not listed | $1.50 blended / 1M $1.00 in / $3.00 out | 2.16s time to first token Artificial Analysis | 43 output tok/sec median | Not listed | May 27, 2026 |
| #45 | ERNIE 5.0 0110 ernie-5.0-0110 | Baidu | Proprietary | 1448#46 1444-1452 CI 34,159 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #46 | Claude Opus 4.1 20250805 claude-opus-4-1-20250805 | Anthropic | Proprietary | 1447#47 1444-1450 CI 77,373 votes | 1386#44 1377-1395 CI 8,565 votes | Not listed | Not listed | Not listed | $32.81 blended / 1M $18.75 in / $75.00 out | 9.84s time to first token Artificial Analysis | 34 output tok/sec median | Not listed | May 27, 2026 |
| #47 | Grok 4.3 grok-4.3 | xAI | Proprietary | 1447#48 1441-1452 CI 15,773 votes | 1377#47 1366-1387 CI 3,482 votes | 1247#25 1236-1258 CI 3,868 votes | 1203#6 1194-1211 CI 6,865 votes | Not listed | $1.56 blended / 1M $1.25 in / $2.50 out | 0.58s time to first token Artificial Analysis | 117 output tok/sec median | Not listed | May 27, 2026 |
| #48 | Gemini 2.5 Pro gemini-2.5-pro | Proprietary | 1446#49 1443-1448 CI 122,636 votes | 1204#75 1190-1217 CI 3,297 votes | 1245#27 1240-1250 CI 87,168 votes | Not listed | Not listed | $3.44 blended / 1M $1.25 in / $10.00 out | Not listed | Not listed | 53.6%#35 bash-only mini 1.0.0 | May 27, 2026 | |
| #49 | Qwen3.5 397b A17B qwen3.5-397b-a17b Open weights | Alibaba | Open weights | 1445#50 1440-1449 CI 31,970 votes | 1393#37 1386-1400 CI 9,663 votes | 1244#29 1236-1251 CI 11,789 votes | Not listed | Not listed | $1.35 blended / 1M $0.600 in / $3.60 out | 1.81s time to first token Artificial Analysis | 52 output tok/sec median | Not listed | May 27, 2026 |
| #50 | GPT-4.5 Preview 2025 02 27 gpt-4.5-preview-2025-02-27 | OpenAI | Proprietary | 1445#51 1439-1450 CI 14,547 votes | Not listed | 1226#38 1215-1238 CI 2,925 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #51 | Qwen3.6 Plus qwen3.6-plus Coding | Alibaba | Proprietary | 1444#52 1439-1450 CI 18,202 votes | 1460#18 1452-1469 CI 6,136 votes | Not listed | Not listed | Not listed | $1.13 blended / 1M $0.500 in / $3.00 out | 1.90s time to first token Artificial Analysis | 53 output tok/sec median | Not listed | May 27, 2026 |
| #52 | ChatGPT 4o Latest 20250326 chatgpt-4o-latest-20250326 | OpenAI | Proprietary | 1443#53 1440-1446 CI 82,471 votes | Not listed | 1241#30 1235-1247 CI 23,443 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #53 | GLM 4.7 glm-4.7 Open weights | Z.ai | Open weights | 1443#54 1436-1449 CI 12,133 votes | 1440#22 1430-1450 CI 4,881 votes | Not listed | Not listed | Not listed | $1.00 blended / 1M $0.600 in / $2.20 out | 0.83s time to first token Artificial Analysis | 83 output tok/sec median | Not listed | May 27, 2026 |
| #54 | GPT-5.1 gpt-5.1 | OpenAI | Proprietary | 1439#55 1435-1442 CI 43,501 votes | 1340#55 1332-1347 CI 12,866 votes | 1238#34 1230-1246 CI 10,119 votes | Not listed | Not listed | $3.44 blended / 1M $1.25 in / $10.00 out | 0.65s time to first token Artificial Analysis | 101 output tok/sec median | Not listed | May 27, 2026 |
| #55 | Gemma 4 26b A4B gemma-4-26b-a4b Open weights | Open weights | 1439#56 1431-1446 CI 5,789 votes | 1360#52 1344-1376 CI 1,502 votes | 1241#31 1233-1249 CI 10,707 votes | Not listed | Not listed | $0.198 blended / 1M $0.130 in / $0.400 out | 0.77s time to first token Artificial Analysis | 62 output tok/sec median | Not listed | May 27, 2026 | |
| #56 | GPT-5.2 High gpt-5.2-high Reasoning | OpenAI | Proprietary | 1438#57 1435-1442 CI 46,111 votes | Not listed | 1245#28 1238-1252 CI 15,221 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #57 | DeepSeek V4 Flash Thinking deepseek-v4-flash-thinking ReasoningOpen weights | DeepSeek | Open weights | 1437#58 1432-1443 CI 16,545 votes | Not listed | Not listed | Not listed | Not listed | $0.175 blended / 1M $0.140 in / $0.280 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #58 | Longcat Flash Chat 2602 Exp longcat-flash-chat-2602-exp | Meituan | Proprietary | 1436#59 1431-1441 CI 23,731 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #59 | Qwen3 Max Preview qwen3-max-preview | Alibaba | Proprietary | 1435#60 1431-1440 CI 27,736 votes | Not listed | Not listed | Not listed | Not listed | $2.40 blended / 1M $1.20 in / $6.00 out | 1.92s time to first token Artificial Analysis | 48 output tok/sec median | Not listed | May 27, 2026 |
| #60 | GPT-5.2 gpt-5.2 | OpenAI | Proprietary | 1435#61 1431-1439 CI 46,492 votes | 1404#32 1388-1421 CI 1,458 votes | 1232#35 1225-1239 CI 16,106 votes | Not listed | Not listed | $4.81 blended / 1M $1.75 in / $14.00 out | Not listed | Not listed | 72.8%#9 bash-only mini 2.0.0 | May 27, 2026 |
| #61 | MiMo V2.5 mimo-v2.5 Open weights | Xiaomi | Open weights | 1434#62 1428-1440 CI 15,979 votes | 1440#23 1430-1450 CI 3,741 votes | 1231#36 1222-1239 CI 6,912 votes | Not listed | Not listed | $0.175 blended / 1M $0.140 in / $0.280 out | 2.13s time to first token Artificial Analysis | 82 output tok/sec median | Not listed | May 27, 2026 |
| #62 | GPT-5 High gpt-5-high Reasoning | OpenAI | Proprietary | 1434#63 1429-1438 CI 31,947 votes | Not listed | 1211#49 1204-1219 CI 35,144 votes | Not listed | Not listed | $3.44 blended / 1M $1.25 in / $10.00 out | 0.56s time to first token Artificial Analysis | 169 output tok/sec median | Not listed | May 27, 2026 |
| #63 | Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-preview | Proprietary | 1433#64 1429-1438 CI 35,135 votes | 1248#68 1240-1256 CI 9,327 votes | 1238#33 1230-1245 CI 14,016 votes | Not listed | Not listed | $0.563 blended / 1M $0.250 in / $1.50 out | 5.06s time to first token Artificial Analysis | 291 output tok/sec median | Not listed | May 27, 2026 | |
| #64 | DeepSeek V4 Flash deepseek-v4-flash Open weights | DeepSeek | Open weights | 1433#65 1427-1438 CI 16,725 votes | Not listed | Not listed | Not listed | Not listed | $0.175 blended / 1M $0.140 in / $0.280 out | 0.96s time to first token Artificial Analysis | 114 output tok/sec median | Not listed | May 27, 2026 |
| #65 | Kimi K2.5 Instant kimi-k2.5-instant Open weights | Moonshot AI | Open weights | 1432#66 1425-1439 CI 8,197 votes | 1408#30 1397-1419 CI 3,612 votes | 1239#32 1228-1250 CI 3,898 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #66 | O3 2025 04 16 o3-2025-04-16 | OpenAI | Proprietary | 1431#67 1428-1435 CI 59,775 votes | Not listed | 1218#44 1211-1225 CI 46,723 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #67 | Grok 4.1 Fast Reasoning grok-4-1-fast-reasoning Reasoning | xAI | Proprietary | 1431#68 1428-1434 CI 54,616 votes | 1234#72 1224-1243 CI 6,911 votes | 1192#57 1184-1199 CI 10,607 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #68 | Kimi K2 Thinking Turbo kimi-k2-thinking-turbo ReasoningOpen weights | Moonshot AI | Open weights | 1430#69 1427-1433 CI 60,235 votes | 1329#59 1323-1336 CI 15,344 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #69 | Amazon Nova Experimental Chat 26 02 10 amazon-nova-experimental-chat-26-02-10 | Amazon | Proprietary | 1427#70 1418-1437 CI 3,418 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #70 | GPT-5 Chat gpt-5-chat | OpenAI | Proprietary | 1427#71 1422-1431 CI 31,595 votes | Not listed | 1226#40 1218-1233 CI 40,848 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #71 | GLM 4.6 glm-4.6 Open weights | Z.ai | Open weights | 1426#72 1422-1430 CI 35,661 votes | 1355#54 1346-1364 CI 8,349 votes | Not listed | Not listed | Not listed | $1.00 blended / 1M $0.600 in / $2.20 out | 1.85s time to first token Artificial Analysis | 45 output tok/sec median | 55.4%#32 bash-only mini 1.17.1 | May 27, 2026 |
| #72 | DeepSeek V3.2 Exp Thinking deepseek-v3.2-exp-thinking ReasoningOpen weights | DeepSeek | Open weights | 1425#73 1418-1431 CI 9,064 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #73 | DeepSeek V3.2 deepseek-v3.2 Open weights | DeepSeek | Open weights | 1424#74 1421-1428 CI 46,204 votes | 1332#58 1325-1339 CI 10,463 votes | Not listed | Not listed | Not listed | $0.775 blended / 1M $0.500 in / $1.60 out | Not listed | Not listed | 70%#15 bash-only mini 2.0.0 | May 27, 2026 |
| #74 | Claude Opus 4 20250514 Thinking 16K claude-opus-4-20250514-thinking-16k Reasoning | Anthropic | Proprietary | 1424#75 1420-1429 CI 36,900 votes | Not listed | 1207#51 1191-1223 CI 1,315 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #75 | Qwen3 Max 2025 09 23 qwen3-max-2025-09-23 | Alibaba | Proprietary | 1424#76 1418-1431 CI 9,158 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #76 | DeepSeek V3.2 Exp deepseek-v3.2-exp Open weights | DeepSeek | Open weights | 1423#77 1417-1430 CI 11,941 votes | 1287#64 1276-1298 CI 4,870 votes | Not listed | Not listed | Not listed | $0.310 blended / 1M $0.275 in / $0.415 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #77 | Qwen3 235b A22B Instruct 2507 qwen3-235b-a22b-instruct-2507 Open weights | Alibaba | Open weights | 1423#78 1421-1426 CI 95,473 votes | Not listed | Not listed | Not listed | Not listed | $0.838 blended / 1M $0.400 in / $2.15 out | 1.25s time to first token Artificial Analysis | 62 output tok/sec median | Not listed | May 27, 2026 |
| #78 | DeepSeek R1 0528 deepseek-r1-0528 Open weights | DeepSeek | Open weights | 1422#79 1417-1428 CI 18,467 votes | Not listed | Not listed | Not listed | Not listed | $2.06 blended / 1M $1.35 in / $4.20 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #79 | DeepSeek V3.2 Thinking deepseek-v3.2-thinking ReasoningOpen weights | DeepSeek | Open weights | 1422#80 1419-1426 CI 40,111 votes | 1368#49 1360-1376 CI 7,908 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #80 | Grok 4 Fast Chat grok-4-fast-chat | xAI | Proprietary | 1421#81 1414-1429 CI 6,820 votes | Not listed | Not listed | Not listed | Not listed | $0.275 blended / 1M $0.200 in / $0.500 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #81 | ERNIE 5.0 Preview 1022 ernie-5.0-preview-1022 | Baidu | Proprietary | 1420#82 1411-1428 CI 4,708 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #82 | Kimi K2 0905 Preview kimi-k2-0905-preview Open weights | Moonshot AI | Open weights | 1418#83 1412-1425 CI 11,795 votes | Not listed | Not listed | Not listed | Not listed | $1.08 blended / 1M $0.600 in / $2.50 out | 1.57s time to first token Artificial Analysis | 25 output tok/sec median | Not listed | May 27, 2026 |
| #83 | DeepSeek V3.1 deepseek-v3.1 Open weights | DeepSeek | Open weights | 1418#84 1412-1424 CI 14,969 votes | Not listed | Not listed | Not listed | Not listed | $0.865 blended / 1M $0.590 in / $1.69 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #84 | DeepSeek V3.1 Terminus Thinking deepseek-v3.1-terminus-thinking ReasoningOpen weights | DeepSeek | Open weights | 1418#85 1408-1428 CI 3,468 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #85 | Kimi K2 0711 Preview kimi-k2-0711-preview Open weights | Moonshot AI | Open weights | 1417#86 1412-1422 CI 27,643 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #86 | Qwen3.5 122b A10B qwen3.5-122b-a10b Open weights | Alibaba | Open weights | 1417#87 1413-1422 CI 26,670 votes | 1365#51 1358-1372 CI 8,148 votes | 1223#41 1215-1231 CI 10,089 votes | Not listed | Not listed | $1.10 blended / 1M $0.400 in / $3.20 out | 1.19s time to first token Artificial Analysis | 151 output tok/sec median | Not listed | May 27, 2026 |
| #87 | DeepSeek V3.1 Thinking deepseek-v3.1-thinking ReasoningOpen weights | DeepSeek | Open weights | 1417#88 1411-1424 CI 11,746 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #88 | DeepSeek V3.1 Terminus deepseek-v3.1-terminus Open weights | DeepSeek | Open weights | 1416#89 1406-1426 CI 3,705 votes | Not listed | Not listed | Not listed | Not listed | $1.91 blended / 1M $1.64 in / $2.75 out | Not listed | Not listed | Not listed | May 27, 2026 |
| #89 | Amazon Nova Experimental Chat 26 01 10 amazon-nova-experimental-chat-26-01-10 | Amazon | Proprietary | 1416#90 1406-1426 CI 3,414 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #90 | Hunyuan Hy3 Preview hunyuan-hy3-preview | Tencent | Proprietary | 1416#91 1408-1424 CI 5,812 votes | 1365#50 1348-1383 CI 1,349 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #91 | Qwen3 VL 235b A22B Instruct qwen3-vl-235b-a22b-instruct Open weights | Alibaba | Open weights | 1415#92 1409-1422 CI 11,515 votes | Not listed | 1215#45 1207-1222 CI 12,232 votes | Not listed | Not listed | $0.700 blended / 1M $0.300 in / $1.90 out | 1.17s time to first token Artificial Analysis | 49 output tok/sec median | Not listed | May 27, 2026 |
| #92 | Mistral Large 3 mistral-large-3 Open weights | Mistral | Open weights | 1415#93 1412-1419 CI 42,553 votes | 1223#73 1203-1243 CI 1,032 votes | Not listed | Not listed | Not listed | $0.750 blended / 1M $0.500 in / $1.50 out | 0.58s time to first token Artificial Analysis | 61 output tok/sec median | Not listed | May 27, 2026 |
| #93 | MiMo V2 Omni mimo-v2-omni | Xiaomi | Proprietary | 1414#94 1403-1425 CI 2,968 votes | Not listed | 1213#48 1204-1221 CI 7,491 votes | Not listed | Not listed | Not listed | 2.26s time to first token Artificial Analysis | 84 output tok/sec median | Not listed | May 27, 2026 |
| #94 | GPT-4.1 2025 04 14 gpt-4.1-2025-04-14 | OpenAI | Proprietary | 1413#95 1410-1417 CI 50,997 votes | Not listed | 1214#46 1208-1221 CI 42,128 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #95 | Minimax M2.7 minimax-m2.7 Open weights | MiniMax | Open weights | 1413#96 1408-1418 CI 23,278 votes | 1401#34 1392-1409 CI 6,332 votes | Not listed | Not listed | Not listed | $0.525 blended / 1M $0.300 in / $1.20 out | 2.86s time to first token Artificial Analysis | 67 output tok/sec median | Not listed | May 27, 2026 |
| #96 | Claude Opus 4 20250514 claude-opus-4-20250514 | Anthropic | Proprietary | 1412#97 1408-1416 CI 44,223 votes | Not listed | 1188#60 1175-1201 CI 2,226 votes | Not listed | Not listed | $32.81 blended / 1M $18.75 in / $75.00 out | 7.55s time to first token Artificial Analysis | 37 output tok/sec median | 67.6%#18 bash-only mini 1.0.0 | May 27, 2026 |
| #97 | Grok 3 Preview 02 24 grok-3-preview-02-24 | xAI | Proprietary | 1412#98 1407-1416 CI 32,909 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 27, 2026 |
| #98 | GLM 4.5 glm-4.5 Open weights | Z.ai | Open weights | 1411#99 1406-1416 CI 24,322 votes | Not listed | Not listed | Not listed | Not listed | $1.00 blended / 1M $0.600 in / $2.20 out | 1.28s time to first token Artificial Analysis | 50 output tok/sec median | 54.2%#33 bash-only mini 1.9.1 | May 27, 2026 |
| #99 | Gemini 2.5 Flash gemini-2.5-flash | Proprietary | 1411#100 1408-1413 CI 122,458 votes | Not listed | 1214#47 1209-1219 CI 57,538 votes | Not listed | Not listed | $0.850 blended / 1M $0.300 in / $2.50 out | 11.0s time to first token Artificial Analysis | 222 output tok/sec median | 28.7%#41 bash-only mini 1.0.0 | May 27, 2026 | |
| #100 | Api GPT 4o Search api-gpt-4o-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1079#28 1067-1090 CI 3,413 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #101 | Claude 3.5 Haiku 20241022 claude-3-5-haiku-20241022 | Anthropic | Proprietary | Not listed | Not listed | 1127#88 1111-1143 CI 1,430 votes | Not listed | Not listed | $1.75 blended / 1M $1.00 in / $4.00 out | Not listed | Not listed | Not listed | May 18, 2026 |
| #102 | Claude 3.5 Sonnet 20240620 claude-3-5-sonnet-20240620 | Anthropic | Proprietary | Not listed | Not listed | 1146#81 1136-1156 CI 21,624 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #103 | Claude 3.5 Sonnet 20241022 claude-3-5-sonnet-20241022 | Anthropic | Proprietary | Not listed | Not listed | 1161#72 1154-1169 CI 10,407 votes | Not listed | Not listed | $6.56 blended / 1M $3.75 in / $15.00 out | Not listed | Not listed | Not listed | May 18, 2026 |
| #104 | Claude 3.7 Sonnet 20250219 claude-3-7-sonnet-20250219 | Anthropic | Proprietary | Not listed | Not listed | 1176#66 1167-1185 CI 4,558 votes | Not listed | Not listed | Not listed | Not listed | Not listed | 52.8%#36 bash-only mini 0.0.0 | May 18, 2026 |
| #105 | Claude 3.7 Sonnet 20250219 Thinking 32K claude-3-7-sonnet-20250219-thinking-32k Reasoning | Anthropic | Proprietary | Not listed | Not listed | 1195#55 1180-1211 CI 1,471 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #106 | Claude Haiku 4.5 20251001 claude-haiku-4-5-20251001 | Anthropic | Proprietary | Not listed | 1322#61 1317-1328 CI 20,550 votes | Not listed | Not listed | Not listed | $2.19 blended / 1M $1.25 in / $5.00 out | 11.4s time to first token Artificial Analysis | 133 output tok/sec median | 66.6%#19 bash-only mini 2.0.0 | May 25, 2026 |
| #107 | Claude Opus 4 Search claude-opus-4-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1150#22 1145-1156 CI 31,129 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #108 | Claude Opus 4.1 Search claude-opus-4-1-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1166#19 1161-1171 CI 71,286 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #109 | Claude Opus 4.5 Search claude-opus-4-5-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1190#14 1184-1196 CI 53,423 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #110 | Claude Opus 4.6 Search claude-opus-4-6-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1219#2 1212-1226 CI 48,724 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #111 | Claude Sonnet 4 20250514 claude-sonnet-4-20250514 | Anthropic | Proprietary | Not listed | Not listed | 1189#59 1175-1203 CI 1,852 votes | Not listed | Not listed | $6.56 blended / 1M $3.75 in / $15.00 out | 9.60s time to first token Artificial Analysis | 46 output tok/sec median | 64.9%#23 bash-only mini 1.0.0 | May 18, 2026 |
| #112 | Claude Sonnet 4 20250514 Thinking 32K claude-sonnet-4-20250514-thinking-32k Reasoning | Anthropic | Proprietary | Not listed | Not listed | 1207#50 1190-1224 CI 1,172 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #113 | Claude Sonnet 4.5 Search claude-sonnet-4-5-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1170#18 1164-1176 CI 45,686 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #114 | Claude Sonnet 4.6 Search claude-sonnet-4-6-search | Anthropic | Proprietary | Not listed | Not listed | Not listed | 1196#12 1189-1202 CI 48,055 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #115 | Devstral 2 devstral-2 Open weights | Mistral | Open weights | Not listed | 1199#77 1182-1216 CI 1,583 votes | Not listed | Not listed | Not listed | Not listed | 0.63s time to first token Artificial Analysis | 42 output tok/sec median | Not listed | May 25, 2026 |
| #116 | Devstral Medium 2507 devstral-medium-2507 | Mistral | Proprietary | Not listed | 1091#81 1069-1114 CI 992 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #117 | Diffbot Small Xl diffbot-small-xl Open weights | Diffbot | Open weights | Not listed | Not listed | Not listed | 1063#29 1054-1071 CI 6,406 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #118 | ERNIE 5.0 Preview 1220 ernie-5.0-preview-1220 | Baidu | Proprietary | Not listed | Not listed | 1219#43 1207-1230 CI 3,191 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #119 | Gemini 1.5 Flash 002 gemini-1.5-flash-002 | Proprietary | Not listed | Not listed | 1141#83 1131-1150 CI 7,241 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #120 | Gemini 1.5 Pro 001 gemini-1.5-pro-001 | Proprietary | Not listed | Not listed | 1120#92 1108-1131 CI 16,734 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #121 | Gemini 1.5 Pro 002 gemini-1.5-pro-002 | Proprietary | Not listed | Not listed | 1179#65 1171-1188 CI 8,902 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #122 | Gemini 2.0 Flash 001 gemini-2.0-flash-001 | Proprietary | Not listed | Not listed | 1171#68 1164-1179 CI 10,241 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #123 | Gemini 2.0 Flash Lite Preview 02 05 gemini-2.0-flash-lite-preview-02-05 | Proprietary | Not listed | Not listed | 1136#85 1125-1146 CI 3,991 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #124 | Gemini 2.5 Flash Lite Preview 06 17 Thinking gemini-2.5-flash-lite-preview-06-17-thinking Reasoning | Proprietary | Not listed | Not listed | 1188#61 1180-1196 CI 36,868 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #125 | Gemini 2.5 Flash Lite Preview 09 2025 No Thinking gemini-2.5-flash-lite-preview-09-2025-no-thinking Reasoning | Proprietary | Not listed | Not listed | 1175#67 1165-1184 CI 4,780 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #126 | Gemini 2.5 Flash Preview 09 2025 gemini-2.5-flash-preview-09-2025 | Proprietary | Not listed | Not listed | 1226#39 1216-1236 CI 4,735 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #127 | Gemini 2.5 Pro Grounding gemini-2.5-pro-grounding | Proprietary | Not listed | Not listed | Not listed | 1143#23 1138-1148 CI 76,776 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 | |
| #128 | Gemini 3 Flash Grounding gemini-3-flash-grounding | Proprietary | Not listed | Not listed | Not listed | 1197#10 1191-1203 CI 62,919 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 | |
| #129 | Gemini 3 Pro Grounding gemini-3-pro-grounding | Proprietary | Not listed | Not listed | Not listed | 1202#7 1196-1207 CI 37,289 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 | |
| #130 | Gemini 3.1 Pro Grounding gemini-3.1-pro-grounding | Proprietary | Not listed | Not listed | Not listed | 1212#4 1205-1219 CI 28,011 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 | |
| #131 | Gemma 3 27b It gemma-3-27b-it | Proprietary | Not listed | Not listed | 1159#73 1151-1167 CI 17,436 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 | |
| #132 | GLM 4.5v glm-4.5v Open weights | Z.ai | Open weights | Not listed | Not listed | 1156#77 1144-1168 CI 3,330 votes | Not listed | Not listed | $0.900 blended / 1M $0.600 in / $1.80 out | 1.18s time to first token Artificial Analysis | 30 output tok/sec median | Not listed | May 18, 2026 |
| #133 | GLM 4.6v glm-4.6v Open weights | Z.ai | Open weights | Not listed | Not listed | 1165#69 1150-1179 CI 2,337 votes | Not listed | Not listed | $0.450 blended / 1M $0.300 in / $0.900 out | 1.40s time to first token Artificial Analysis | 60 output tok/sec median | Not listed | May 18, 2026 |
| #134 | GLM 5v Turbo glm-5v-turbo | Z.ai | Proprietary | Not listed | Not listed | 1227#37 1219-1236 CI 7,480 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #135 | GPT 4o 2024 05 13 gpt-4o-2024-05-13 | OpenAI | Proprietary | Not listed | Not listed | 1163#70 1154-1171 CI 23,273 votes | Not listed | Not listed | $7.50 blended / 1M $5.00 in / $15.00 out | 0.55s time to first token Artificial Analysis | 92 output tok/sec median | Not listed | May 18, 2026 |
| #136 | GPT 4o 2024 08 06 gpt-4o-2024-08-06 | OpenAI | Proprietary | Not listed | Not listed | 1119#93 1107-1131 CI 3,376 votes | Not listed | Not listed | $4.38 blended / 1M $2.50 in / $10.00 out | 0.54s time to first token Artificial Analysis | 92 output tok/sec median | Not listed | May 18, 2026 |
| #137 | GPT 4o Mini 2024 07 18 gpt-4o-mini-2024-07-18 | OpenAI | Proprietary | Not listed | Not listed | 1098#96 1090-1106 CI 17,342 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #138 | GPT-4 Turbo 2024 04 09 gpt-4-turbo-2024-04-09 | OpenAI | Proprietary | Not listed | Not listed | 1113#94 1101-1124 CI 13,391 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #139 | GPT-4.1 Mini 2025 04 14 gpt-4.1-mini-2025-04-14 | OpenAI | Proprietary | Not listed | Not listed | 1203#52 1195-1211 CI 41,367 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #140 | GPT-4.1 Nano 2025 04 14 gpt-4.1-nano-2025-04-14 | OpenAI | Proprietary | Not listed | Not listed | 1090#98 1071-1108 CI 1,211 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #141 | GPT-5 Medium gpt-5-medium | OpenAI | Proprietary | Not listed | 1394#36 1381-1407 CI 3,754 votes | Not listed | Not listed | Not listed | $3.44 blended / 1M $1.25 in / $10.00 out | 40.0s time to first token Artificial Analysis | 86 output tok/sec median | Not listed | May 25, 2026 |
| #142 | GPT-5 Mini High gpt-5-mini-high Reasoning | OpenAI | Proprietary | Not listed | Not listed | 1182#63 1174-1190 CI 29,641 votes | Not listed | Not listed | $0.688 blended / 1M $0.250 in / $2.00 out | 15.3s time to first token Artificial Analysis | 88 output tok/sec median | Not listed | May 18, 2026 |
| #143 | GPT-5 Nano High gpt-5-nano-high Reasoning | OpenAI | Proprietary | Not listed | Not listed | 1148#79 1136-1159 CI 4,027 votes | Not listed | Not listed | $0.138 blended / 1M $0.050 in / $0.400 out | 86.2s time to first token Artificial Analysis | 155 output tok/sec median | Not listed | May 18, 2026 |
| #144 | GPT-5 Search gpt-5-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1179#17 1171-1187 CI 20,839 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #145 | GPT-5.1 Codex gpt-5.1-codex | OpenAI | Proprietary | Not listed | 1329#60 1320-1339 CI 6,216 votes | Not listed | Not listed | Not listed | $3.44 blended / 1M $1.25 in / $10.00 out | 4.02s time to first token Artificial Analysis | 189 output tok/sec median | 66%#20 bash-only mini 1.16.0 | May 25, 2026 |
| #146 | GPT-5.1 Codex Mini gpt-5.1-codex-mini | OpenAI | Proprietary | Not listed | 1240#70 1222-1257 CI 1,443 votes | Not listed | Not listed | Not listed | $0.688 blended / 1M $0.250 in / $2.00 out | 3.79s time to first token Artificial Analysis | 211 output tok/sec median | Not listed | May 25, 2026 |
| #147 | GPT-5.1 Medium gpt-5.1-medium | OpenAI | Proprietary | Not listed | 1391#39 1382-1401 CI 6,115 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #148 | GPT-5.1 Search gpt-5.1-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1181#16 1175-1187 CI 53,667 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #149 | GPT-5.2 Codex gpt-5.2-codex | OpenAI | Proprietary | Not listed | 1335#57 1327-1342 CI 7,766 votes | Not listed | Not listed | Not listed | $4.81 blended / 1M $1.75 in / $14.00 out | 2.19s time to first token Artificial Analysis | 108 output tok/sec median | 72.8%#7 bash-only mini 2.0.0 | May 25, 2026 |
| #150 | GPT-5.2 Search gpt-5.2-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1163#20 1157-1169 CI 47,097 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #151 | GPT-5.2 Search Non Reasoning gpt-5.2-search-non-reasoning Reasoning | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1140#25 1134-1147 CI 65,549 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #152 | GPT-5.3 Codex gpt-5.3-codex (codex-harness) | OpenAI | Proprietary | Not listed | 1373#48 1362-1384 CI 3,546 votes | Not listed | Not listed | Not listed | $4.81 blended / 1M $1.75 in / $14.00 out | 69.7s time to first token Artificial Analysis | 73 output tok/sec median | Not listed | May 25, 2026 |
| #153 | GPT-5.4 Medium gpt-5.4-medium (codex-harness) | OpenAI | Proprietary | Not listed | 1437#25 1421-1454 CI 1,449 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #154 | GPT-5.4 Nano High gpt-5.4-nano-high Reasoning | OpenAI | Proprietary | Not listed | Not listed | 1200#54 1191-1208 CI 8,557 votes | Not listed | Not listed | $0.463 blended / 1M $0.200 in / $1.25 out | 3.31s time to first token Artificial Analysis | 160 output tok/sec median | Not listed | May 18, 2026 |
| #155 | GPT-5.4 Search gpt-5.4-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1199#9 1191-1206 CI 27,862 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #156 | GPT-5.5 Search gpt-5.5-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1223#1 1215-1231 CI 9,492 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #157 | GPT-5.5 xHigh gpt-5.5-xhigh (codex-harness) ReasoningCoding | OpenAI | Proprietary | Not listed | 1505#11 1495-1515 CI 4,126 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #158 | Granite 4.1 8b granite-4.1-8b Open weights | IBM | Open weights | Not listed | 1202#76 1184-1220 CI 1,725 votes | Not listed | Not listed | Not listed | $0.063 blended / 1M $0.050 in / $0.100 out | 0.38s time to first token Artificial Analysis | 133 output tok/sec median | Not listed | May 25, 2026 |
| #159 | Grok 4 0709 grok-4-0709 | xAI | Proprietary | Not listed | Not listed | 1182#64 1175-1189 CI 32,756 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #160 | Grok 4 Fast Reasoning grok-4-fast-reasoning Reasoning | xAI | Proprietary | Not listed | 1150#79 1126-1173 CI 933 votes | Not listed | Not listed | Not listed | $0.275 blended / 1M $0.200 in / $0.500 out | Not listed | Not listed | Not listed | May 25, 2026 |
| #161 | Grok 4 Fast Search grok-4-fast-search | xAI | Proprietary | Not listed | Not listed | Not listed | 1159#21 1154-1164 CI 42,951 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #162 | Grok 4 Search grok-4-search | xAI | Proprietary | Not listed | Not listed | Not listed | 1121#27 1115-1127 CI 19,303 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #163 | Grok 4.1 Fast Search grok-4-1-fast-search | xAI | Proprietary | Not listed | Not listed | Not listed | 1196#11 1190-1201 CI 71,617 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #164 | Grok Code Fast 1 grok-code-fast-1 | xAI | Proprietary | Not listed | 1140#80 1118-1162 CI 982 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #165 | Hunyuan Large Vision hunyuan-large-vision | Tencent | Proprietary | Not listed | Not listed | 1148#78 1132-1165 CI 1,305 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #166 | Hunyuan Vision 1.5 Thinking hunyuan-vision-1.5-thinking Reasoning | Tencent | Proprietary | Not listed | Not listed | 1162#71 1149-1174 CI 2,429 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #167 | KAT Coder Pro V1 KAT-Coder-Pro-V1 | Unknown | Proprietary | Not listed | 1259#66 1243-1274 CI 1,881 votes | Not listed | Not listed | Not listed | $0.525 blended / 1M $0.300 in / $1.20 out | 1.71s time to first token Artificial Analysis | 115 output tok/sec median | Not listed | May 25, 2026 |
| #168 | Llama 4 Maverick 17b 128e Instruct llama-4-maverick-17b-128e-instruct | Meta | Proprietary | Not listed | Not listed | 1147#80 1138-1157 CI 7,063 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #169 | Llama 4 Scout 17b 16e Instruct llama-4-scout-17b-16e-instruct | Meta | Proprietary | Not listed | Not listed | 1129#87 1119-1138 CI 6,552 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #170 | Mercury 2 mercury-2 | Inception AI | Proprietary | Not listed | 1165#78 1143-1188 CI 946 votes | Not listed | Not listed | Not listed | $0.375 blended / 1M $0.250 in / $0.750 out | 2.94s time to first token Artificial Analysis | 950 output tok/sec median | Not listed | May 25, 2026 |
| #171 | MiMo V2 Flash mimo-v2-flash (non-thinking) ReasoningOpen weights | Xiaomi | Open weights | Not listed | 1300#63 1286-1314 CI 2,098 votes | Not listed | Not listed | Not listed | $0.150 blended / 1M $0.100 in / $0.300 out | 1.32s time to first token Artificial Analysis | 130 output tok/sec median | Not listed | May 25, 2026 |
| #172 | Minimax M2 minimax-m2 Open weights | MiniMax | Open weights | Not listed | 1305#62 1296-1314 CI 8,394 votes | Not listed | Not listed | Not listed | $0.525 blended / 1M $0.300 in / $1.20 out | 1.04s time to first token Artificial Analysis | 110 output tok/sec median | 61%#25 bash-only mini 1.17.0 | May 25, 2026 |
| #173 | Minimax M2.1 Preview minimax-m2.1-preview Open weights | MiniMax | Open weights | Not listed | 1392#38 1383-1400 CI 9,275 votes | Not listed | Not listed | Not listed | $0.525 blended / 1M $0.300 in / $1.20 out | 2.36s time to first token Artificial Analysis | 181 output tok/sec median | Not listed | May 25, 2026 |
| #174 | Minimax M2.5 minimax-m2.5 Open weights | MiniMax | Open weights | Not listed | 1382#45 1374-1390 CI 7,842 votes | Not listed | Not listed | Not listed | $0.525 blended / 1M $0.300 in / $1.20 out | 2.33s time to first token Artificial Analysis | 204 output tok/sec median | 75.8%#3 bash-only mini 2.0.0 | May 25, 2026 |
| #175 | Mistral Medium 2505 mistral-medium-2505 | Mistral | Proprietary | Not listed | Not listed | 1157#76 1148-1165 CI 11,003 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #176 | Mistral Medium 2508 mistral-medium-2508 | Mistral | Proprietary | Not listed | Not listed | 1159#74 1152-1165 CI 42,203 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #177 | Mistral Small 2506 mistral-small-2506 Open weights | Mistral | Open weights | Not listed | Not listed | 1141#84 1132-1150 CI 11,153 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #178 | Mistral Small 3.1 24b Instruct 2503 mistral-small-3.1-24b-instruct-2503 Open weights | Mistral | Open weights | Not listed | Not listed | 1129#86 1120-1137 CI 29,358 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #179 | Molmo 2 8b molmo-2-8b Open weights | Ai2 | Open weights | Not listed | Not listed | 1108#95 1088-1128 CI 1,170 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #180 | O1 2024 12 17 o1-2024-12-17 | OpenAI | Proprietary | Not listed | Not listed | 1194#56 1183-1204 CI 3,694 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #181 | O3 Search o3-search | OpenAI | Proprietary | Not listed | Not listed | Not listed | 1188#15 1181-1195 CI 20,700 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #182 | O4 Mini 2025 04 16 o4-mini-2025-04-16 | OpenAI | Proprietary | Not listed | Not listed | 1202#53 1195-1209 CI 42,415 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #183 | Pixtral Large 2411 pixtral-large-2411 | Mistral | Proprietary | Not listed | Not listed | 1095#97 1086-1104 CI 5,423 votes | Not listed | Not listed | $3.00 blended / 1M $2.00 in / $6.00 out | 0.74s time to first token Artificial Analysis | 60 output tok/sec median | Not listed | May 18, 2026 |
| #184 | Ppl Sonar Pro High ppl-sonar-pro-high Reasoning | Perplexity | Proprietary | Not listed | Not listed | Not listed | 1141#24 1136-1147 CI 28,623 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #185 | Ppl Sonar Reasoning Pro High ppl-sonar-reasoning-pro-high Reasoning | Perplexity | Proprietary | Not listed | Not listed | Not listed | 1138#26 1132-1144 CI 29,136 votes | Not listed | Not listed | Not listed | Not listed | Not listed | May 12, 2026 |
| #186 | Qwen VL Max 1119 qwen-vl-max-1119 | Alibaba | Proprietary | Not listed | Not listed | 1086#99 1070-1102 CI 1,422 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #187 | Qwen VL Max 2025 08 13 qwen-vl-max-2025-08-13 | Alibaba | Proprietary | Not listed | Not listed | 1188#62 1175-1200 CI 3,235 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #188 | Qwen2 VL 72b qwen2-vl-72b | Alibaba | Proprietary | Not listed | Not listed | 1086#100 1076-1096 CI 5,937 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #189 | Qwen2.5 VL 32b Instruct qwen2.5-vl-32b-instruct Open weights | Alibaba | Open weights | Not listed | Not listed | 1121#91 1105-1136 CI 1,490 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #190 | Qwen2.5 VL 72b Instruct qwen2.5-vl-72b-instruct | Alibaba | Proprietary | Not listed | Not listed | 1122#90 1112-1133 CI 3,768 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #191 | Qwen3 Coder 480b A35B Instruct qwen3-coder-480b-a35b-instruct Open weights | Alibaba | Open weights | Not listed | 1282#65 1275-1288 CI 15,207 votes | Not listed | Not listed | Not listed | $0.675 blended / 1M $0.300 in / $1.80 out | 1.63s time to first token Artificial Analysis | 64 output tok/sec median | 55.4%#31 bash-only mini 1.0.0 | May 25, 2026 |
| #192 | Qwen3 VL 235b A22B Thinking qwen3-vl-235b-a22b-thinking ReasoningOpen weights | Alibaba | Open weights | Not listed | Not listed | 1190#58 1177-1202 CI 2,370 votes | Not listed | Not listed | $2.17 blended / 1M $0.840 in / $6.18 out | 2.49s time to first token Artificial Analysis | 33 output tok/sec median | Not listed | May 18, 2026 |
| #193 | Qwen3.5 27b qwen3.5-27b Open weights | Alibaba | Open weights | Not listed | 1358#53 1350-1365 CI 7,663 votes | 1221#42 1214-1229 CI 9,430 votes | Not listed | Not listed | $0.825 blended / 1M $0.300 in / $2.40 out | 1.36s time to first token Artificial Analysis | 83 output tok/sec median | Not listed | May 25, 2026 |
| #194 | Qwen3.5 35b A3B qwen3.5-35b-a3b Open weights | Alibaba | Open weights | Not listed | 1249#67 1234-1265 CI 1,815 votes | Not listed | Not listed | Not listed | $0.688 blended / 1M $0.250 in / $2.00 out | 1.30s time to first token Artificial Analysis | 132 output tok/sec median | Not listed | May 25, 2026 |
| #195 | Qwen3.5 Flash qwen3.5-flash | Alibaba | Proprietary | Not listed | 1237#71 1220-1254 CI 1,562 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #196 | Qwen3.7 Max 20260517 qwen3.7-max-20260517 Coding | Alibaba | Proprietary | Not listed | 1541#4 1525-1557 CI 1,522 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 25, 2026 |
| #197 | Qwen3.7 Plus Preview qwen3.7-plus-preview Multimodal | Alibaba | Proprietary | Not listed | Not listed | 1260#16 1249-1271 CI 3,649 votes | Not listed | Not listed | $0.590 blended / 1M $0.400 in / $1.16 out | 1.33s time to first token Artificial Analysis | 54 output tok/sec median | Not listed | May 18, 2026 |
| #198 | Step 1o Turbo 202506 step-1o-turbo-202506 | Stepfun | Proprietary | Not listed | Not listed | 1158#75 1144-1172 CI 1,942 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #199 | Step 1o Vision 32K Highres step-1o-vision-32k-highres Reasoning | Stepfun | Proprietary | Not listed | Not listed | 1126#89 1113-1138 CI 2,833 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #200 | Step 3 step-3 Open weights | Stepfun | Open weights | Not listed | Not listed | 1145#82 1134-1157 CI 3,303 votes | Not listed | Not listed | Not listed | Not listed | Not listed | Not listed | May 18, 2026 |
| #201 | Trinity Large Thinking trinity-large-thinking ReasoningOpen weights | Unknown | Open weights | Not listed | 1245#69 1226-1264 CI 1,309 votes | Not listed | Not listed | Not listed | $0.395 blended / 1M $0.235 in / $0.875 out | 0.74s time to first token Artificial Analysis | 173 output tok/sec median | Not listed | May 25, 2026 |
Benchmark guide
A quick reading key for comparing models without over-interpreting small differences or missing source data.
Text, Code, Vision, Search, and Docs are separate public Arena views. They compare models in head-to-head preference evaluations for the specific task type, so scores should be read within each column rather than as one universal intelligence number.
The main score is the leaderboard rating and the rank is that model's position in the same Arena view. CI is the confidence interval around the score, and votes show the amount of comparison data behind it. When confidence intervals overlap, small rank gaps deserve extra caution.
SWE-bench tracks how often a model solves real software-engineering issues from GitHub repositories. The table uses matched benchmark rows for model-level comparison, with higher percentages indicating more verified tasks solved.
Price is the estimated blended cost per one million tokens. Latency is time to first token, so lower is better. Speed is output throughput after generation begins, so higher is better.
An empty cell usually means the model is not listed in that source, the benchmark has not published a comparable score, or the public model name could not be matched confidently. It should not be treated as a zero score.
