Thoughts on AI, technology, and the future we're building.

New posts every week

HomeAll PostsAI NewsAI Basics
Timelines
ChatGPTOpenAI release historyAnthropic ClaudeClaude release historyGoogle GeminiGemini release history
Benchmarks
OverviewFull model trackerValue RankingsPerformance for the moneyCoding RankingsSWE-bench and code signalsAgent RankingsTool and workflow signalsReasoning RankingsKnowledge and reasoningLong ContextDocument and retrieval signalsLab ComparisonsProvider-level rankings
CategoriesAboutContact

Subscribe to Newsletter

Practical AI news, tips, tricks, tool analysis, sent straight to your inbox.

No spam. Unsubscribe anytime.

Practical explainers, tool notes, and systems thinking for people turning new AI capability into useful work.

Explore

  • All Posts
  • Categories
  • About
  • Contact

Categories

  • AI News
  • AI Basics
  • ChatGPT
  • Anthropic
  • AI Tools
  • AI Video
  • AI Images
  • Courses

Connect

LinkedInTwitterRSS

© 2026. All rights reserved.

Benchmark suiteUpdated May 27, 2026

Qwen3 Coder 480b A35B Instruct.

A model-level benchmark profile for Qwen3 Coder 480b A35B Instruct, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Alibaba lab page

Lab

Alibaba

Open weights

Coverage

56%

5 of 9 tracked signals

Best Arena rank

#65

WebDev Arena

Best suite

#46

Value / 59

OverviewFull public trackerValuePerformance for the moneyCodingCode and SWE-bench signalsAgentsTool and workflow readinessReasoningKnowledge and reasoning signalsContextDocument and retrieval signalsLabsProvider comparisons

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Qwen3 Coder 480b A35B Instruct is strongest on value.

56% coverage

Its best composite result is rank #46 in the value view, with a 59 value index. The strongest raw Arena signal is WebDev Arena at rank #65 with 15,207 public votes.

Best current lane

Value

#46 / 59 value index

Strongest raw signal

Code

#65, 1282 score

Commercial posture

$0.675

1.64s first token / 61 tok/s

Coverage gaps

Text ArenaVision ArenaSearch ArenaDocument Arena

Profile completeness

5 of 9 signals matched

56%

Arena categories

1/5

Code

Commercial match

Live

Qwen3 Coder 480B A35B Instruct

SWE-bench

#31

bash-only

Raw identifier

qwen3-coder-480b-a35b-instruct

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

WebDev Arena

Arena category

1,282#65

1275-1288 CI

15,207 votes

May 25, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

55.4%#31

bash-only

Qwen3-Coder-480B-A35B-Instruct

Aug 2, 2025

SWE-bench Verified

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$0.675

USD / 1M tokens

Input price

$0.300

USD / 1M input tokens

Output price

$1.80

USD / 1M output tokens

Latency

1.64s

Median time to first token

Output speed

61 tok/s

Median generation speed

Matched source row

Qwen3 Coder 480B A35B Instruct

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#4659

value index

blended / 1M tokens$0.675
time to first token1.64s
output speed61 tok/s

Coding

Code Arena, SWE-bench, and output speed

#6443

coding index

Code Arena rank #651,282
SWE-bench rank #3155.4%
output speed61 tok/s

Agents

Search, documents, code, and latency

#8165

agent proxy

Search ArenaNot listed
Docs ArenaNot listed
latency1.64s

Reasoning

Text, documents, vision, and mode signal

Not listed

Not enough matched source rows for this composite view.

Long context

Document, search, and text benchmark proxy

Not listed

Not enough matched source rows for this composite view.

Lab context

Nearby Alibaba profiles.

Same-lab models make it easier to see whether this profile is a flagship, value play, specialist, or lower-coverage row.

Full lab

Qwen3.7 Max 20260517

qwen3.7-max-20260517

Proprietary

Best rank

#4

Coverage

11%

Qwen3.6 Max Preview

qwen3.6-max-preview

Proprietary

Best rank

#13

Coverage

56%

Qwen3.7 Max Preview

qwen3.7-max-preview

Proprietary

Best rank

#15

Coverage

44%

Qwen3.7 Plus Preview

qwen3.7-plus-preview

Proprietary

Best rank

#16

Coverage

11%

Qwen3.6 Plus

qwen3.6-plus

Proprietary

Best rank

#18

Coverage

56%

Qwen3.5 Max Preview

qwen3.5-max-preview

Proprietary

Best rank

#26

Coverage

11%

Qwen3.5 397b A17B

qwen3.5-397b-a17b

Open weights

Best rank

#29

Coverage

67%

Qwen3.5 122b A10B

qwen3.5-122b-a10b

Open weights

Best rank

#41

Coverage

67%