Benchmark suiteLatest source data: Sep 1, 2026Checked: September 2, 2026

Model value rankings.

A focused view of which frontier models deliver the strongest benchmark signal for the money, balancing quality, blended token price, latency, and output speed.

Ranked models

92

Require quality and price matches

Best value

Gemini 3.7 Flash High

84 value index

Lowest price

$0.100

Hy3

Fastest TTFT

0.40s

Muse Glimmer

Value formula

Quality first, then cost and speed.

The value index normalizes each available signal before blending benchmark quality, blended price, time to first token, and output speed. It avoids raw score-per-dollar math, which can wildly overstate very cheap models.

Best models for the money

Higher value index is better. Missing source rows are omitted from the value ranking rather than treated as zero.

Top 30 of 92

#1
Gemini 3.7 Flash High

gemini-3.7-flash-high

GoogleProprietary
84value index
Price
$1.50blended / 1M tokens
Latency
5.40stime to first token
Speed
286 tok/soutput speed
Quality
76quality signal
ArenaArtificial Analysis
#2
Qwen3.8 Flash Next

qwen3.8-flash-next

AlibabaProprietary
81value index
Price
$0.230blended / 1M tokens
Latency
1.27stime to first token
Speed
84 tok/soutput speed
Quality
81quality signal
ArenaArtificial Analysis
#3
Muse Spark 1.1

muse-spark-1.1

MetaProprietary
81value index
Price
$2.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
74quality signal
ArenaArtificial Analysis
#4
Claude Opus 4.6 Thinking

claude-opus-4-6-thinking

AnthropicProprietary
80value index
Price
$10.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
87quality signal
ArenaArtificial Analysis
#5
Qwen3.8 Max

qwen3.8-max

AlibabaProprietary
78value index
Price
$3.00blended / 1M tokens
Latency
1.41stime to first token
Speed
40 tok/soutput speed
Quality
83quality signal
ArenaArtificial Analysis
#6
Claude Opus 4.7

claude-opus-4-7

AnthropicProprietary
76value index
Price
$10.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
81quality signal
ArenaArtificial Analysis
#7
Claude Opus 4.6

claude-opus-4-6

AnthropicProprietary
76value index
Price
$10.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
81quality signal
ArenaArtificial Analysis
#8
Gemini 3.6 Flash High

gemini-3.6-flash-high

GoogleProprietary
75value index
Price
$1.50blended / 1M tokens
Latency
12.9stime to first token
Speed
161 tok/soutput speed
Quality
69quality signal
ArenaArtificial Analysis
#9
GLM 5.3 Flash

glm-5.3-flash

Z.aiOpen weights
74value index
Price
$0.237blended / 1M tokens
Latency
1.43stime to first token
Speed
42 tok/soutput speed
Quality
70quality signal
ArenaArtificial Analysis
#10
Gemini 3.5 Flash High

gemini-3.5-flash-high

GoogleProprietary
74value index
Price
$3.38blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
65quality signal
ArenaArtificial Analysis
#11
Claude Opus 5 High

claude-opus-5-high

AnthropicProprietary
73value index
Price
$10.00blended / 1M tokens
Latency
6.71stime to first token
Speed
47 tok/soutput speed
Quality
86quality signal
ArenaArtificial Analysis
#12
Muse Spark 1.2

muse-spark-1.2 (xHigh)

MetaProprietary
73value index
Price
$2.00blended / 1M tokens
Latency
33.3stime to first token
Speed
77 tok/soutput speed
Quality
79quality signal
ArenaArtificial Analysis
#13
Gemini 3.5 Flash Medium

gemini-3.5-flash-medium

GoogleProprietary
72value index
Price
$3.38blended / 1M tokens
Latency
9.01stime to first token
Speed
232 tok/soutput speed
Quality
61quality signal
ArenaArtificial Analysis
#14
GPT-5.6 Sol xHigh

gpt-5.6-sol-xhigh

OpenAIProprietary
71value index
Price
$8.00blended / 1M tokens
Latency
16.2stime to first token
Speed
76 tok/soutput speed
Quality
81quality signal
ArenaArtificial Analysis
#15
Gemini 3.5 Flash Lite

gemini-3.5-flash-lite

GoogleProprietary
71value index
Price
$0.850blended / 1M tokens
Latency
7.18stime to first token
Speed
322 tok/soutput speed
Quality
47quality signal
ArenaArtificial Analysis
#16
Claude Sonnet 4.6

claude-sonnet-4-6

AnthropicProprietary
70value index
Price
$6.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
64quality signal
ArenaArtificial Analysis
#17
Qwen3.7 Max Preview

qwen3.7-max-preview

AlibabaProprietary
69value index
Price
$3.75blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
59quality signal
ArenaArtificial Analysis
#18
Gemini 3 Pro

gemini-3-pro

GoogleProprietary
69value index
Price
$4.50blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
60quality signal
ArenaArtificial Analysis
#19
Grok 4.5

grok-4.5

xAIProprietary
67value index
Price
$3.00blended / 1M tokens
Latency
11.5stime to first token
Speed
48 tok/soutput speed
Quality
65quality signal
ArenaArtificial Analysis
#20
Claude Opus 4.8

claude-opus-4-8

AnthropicProprietary
67value index
Price
$10.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
68quality signal
ArenaArtificial Analysis
#21
GPT-5.6 Terra xHigh

gpt-5.6-terra-xhigh

OpenAIProprietary
67value index
Price
$4.50blended / 1M tokens
Latency
2.56stime to first token
Speed
87 tok/soutput speed
Quality
62quality signal
ArenaArtificial Analysis
#22
GPT-5.6 Luna xHigh

gpt-5.6-luna-xhigh

OpenAIProprietary
67value index
Price
$0.450blended / 1M tokens
Latency
2.33stime to first token
Speed
110 tok/soutput speed
Quality
52quality signal
ArenaArtificial Analysis
#23
Claude Sonnet 5 High

claude-sonnet-5-high

AnthropicProprietary
67value index
Price
$4.00blended / 1M tokens
Latency
1.34stime to first token
Speed
60 tok/soutput speed
Quality
61quality signal
ArenaArtificial Analysis
#24
Kimi K2.6

kimi-k2.6

Moonshot AIOpen weights
67value index
Price
$1.71blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
52quality signal
ArenaArtificial Analysis
#25
GPT-5.5 High

gpt-5.5-high

OpenAIProprietary
66value index
Price
$11.25blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
67quality signal
ArenaArtificial Analysis
#26
GLM 5.1

glm-5.1

Z.aiOpen weights
65value index
Price
$2.14blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
50quality signal
ArenaArtificial Analysis
#27
Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

GoogleProprietary
64value index
Price
$4.50blended / 1M tokens
Latency
24.6stime to first token
Speed
113 tok/soutput speed
Quality
61quality signal
ArenaArtificial Analysis
#28
Qwen3.7 Plus

qwen3.7-plus

AlibabaProprietary
64value index
Price
$0.700blended / 1M tokens
Latency
1.42stime to first token
Speed
56 tok/soutput speed
Quality
49quality signal
ArenaArtificial Analysis
#29
GPT-5.5

gpt-5.5

OpenAIProprietary
63value index
Price
$11.25blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
63quality signal
ArenaArtificial Analysis
#30
GPT-5.4

gpt-5.4

OpenAIProprietary
63value index
Price
$5.63blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
53quality signal
ArenaArtificial Analysis

Benchmark guide

What the scores mean.

A quick reading key for interpreting the value rankings without over-weighting one benchmark, price point, or speed measurement.

Higher: value indexLower: price + latency
What does the value index measure?

The value index blends normalized benchmark quality, blended token price, latency, and output speed. It is designed to answer which models deliver strong public performance for the money, not which model is best in every task.

Why not use raw score divided by price?

Raw score-per-dollar can exaggerate extremely cheap models and make small benchmark differences look larger than they are. Normalizing each signal keeps the ranking easier to compare across quality, price, and speed.

Why are some models missing from value rankings?

A model needs both a benchmark quality signal and a confident price match to be ranked. If the price or benchmark source is missing, the model is omitted rather than treated as free or zero quality.

How should I use price, latency, and speed together?

Price estimates cost, latency measures time to first token, and speed measures output throughput after generation begins. The best model for a product depends on which constraint matters most in the actual workflow.