Skip to main content

Qwen: Qwen3.7 Max

Qwen: Qwen3.7 Max is qwen's model. On the un-leaked meo benchmark it ranks #5 of 22 with 56.6% accuracy and an Effective Value (𝕍) of 0.0003 β€” earning a correct answer for about $0.0320 in 201s each.

as of 2026-06-08

meo rank
#5
of 22
Accuracy
56.6%
overall
𝕍 index (top=100)
0.58
raw 𝕍 0.0003 Β· N=10
$ / correct
$0.0320
201s each

Per-domain accuracy

CSP (unsatisfiable)
100%
Tape machine
100%
Theory of mind
100%
Regex automaton
100%
Watson-Glaser
75%
Framework bias
67%
Long arithmetic
27%
Logic / math / CS
8%
Base-rate bias
5%
State tracking
0%

Efficiency

Cost per correct
$0.0320
Seconds per correct
201
Tokens per correct
8,309
Correct answers
64 / 151
Total benchmark cost
$2.05
Avg tokens / item
3,522

Aggregated third-party benchmarks

Artificial Analysis (artificialanalysis.ai). Redistribution requires an AA commercial license.

Model details

Lab
qwen
Released
2026-05-21
Weights
β€”
Context
1M
Max output
66K
Knowledge cutoff
β€”
Price in
$1.25/M
Price out
$3.75/M
Modality
text->text

Sources: openrouter Β· artificial_analysis Β· meo

FAQ

How accurate is Qwen: Qwen3.7 Max?

Qwen: Qwen3.7 Max scores 56.6% overall on the meo benchmark (rank #5 of 22), an un-leaked private holdout graded objective-first.

What is Qwen: Qwen3.7 Max's Effective Value?

Its Effective Value (𝕍) is 0.0003 at N=10, Ο‰=1, Ξ΄=1.5 β€” a fused metric of accuracy, speed, cost, and error-cascade. 𝕍 rankings shift with task depth.

How much does Qwen: Qwen3.7 Max cost per correct answer?

About $0.0320 per correct answer (8,309 tokens, 201 seconds each) at benchmark-time pricing via OpenRouter.

Is Qwen: Qwen3.7 Max open weights?

Open-weights status for Qwen: Qwen3.7 Max is not recorded.

Qwen: Qwen3.7 Max β€” meo benchmark, Effective Value & pricing |…