EnterpriseOps-Gym-AA ↗45.00%
Qwen3.7 Max · EnterpriseOps-Gym-AA ↗
Qwen / MODEL EVIDENCE
Qwen3.7 Max
40 benchmarks · 43 observations · 42 sources · released 2026-05-19
Scores at a glance
40 benchmarks · large dot: Qwen3.7 Max; small dots: closest models where reported
ITBench-AA ↗42.47%
Qwen3.7 Max · ITBench-AA · root-cause score ↗
IFBench ↗80.54%
Qwen3.7 Max · IFBench · AA implementation ↗
Terminal-Bench Hard ↗50.76%
Qwen3.7 Max · Terminal-Bench Hard ↗
τ²-Bench Telecom ↗94.74%
Qwen3.7 Max · τ²-Bench Telecom ↗
ErdősBench ↗2.370 / 4
Qwen 3.7 Max · ErdősBench · mean progress / 4 · API ↗
GPQA Diamond ↗90.15 %
Qwen 3.7 Max · GPQA Diamond · Accuracy ↗
1 more reported result
90.91% · Qwen3.7 Max · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
Qwen3.7 Max · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % ↗
Qwen3.7 Max · FrontierMath-Tier-4-v2-Private · Best score (across scorers) · % ↗
Qwen3.7 Max · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
SWE-bench Verified ↗77.27%
Qwen3.7 Max · SWE-Bench verified · Best score (across scorers) · % ↗
1 more reported result
68.8 % · Qwen 3.7 Max (Mini-SWE-agent) · SWE-bench Verified · Score · Vals AI · SWE-bench Verified ↗
SimpleQA Verified ↗55.77%
Qwen3.7 Max · SimpleQA Verified · Best score (across scorers) · % ↗
Qwen3.7 Max · Chess Puzzles · Best score (across scorers) · % ↗
Qwen3.7 Max · EBR-bench · Best score (across scorers) · % ↗
Qwen3.7 Max · Mystery Game Puzzles · Best score (across scorers) · % ↗
1 more reported result
26% · Qwen3.7-Max · Mystery Game Puzzles · Best score (across scorers) · % · Epoch AI · Mystery Game Puzzles ↗
SimpleBench ↗70.4%
Qwen3.7 Max · SimpleBench · Score (AVG@5) · % ↗
GBAEval ↗0.41%
Qwen3.7 Max · GBAEval · Overall score · % ↗
CritPt ↗13.43%
Qwen3.7 Max · CritPt · Accuracy · % ↗
ProofBench ↗26%
Qwen3.7 Max · ProofBench · Accuracy · % ↗
LMCA ↗44.02%
Qwen3.7 Max · LMCA · Score · % ↗
DTBench ↗92.27%
Qwen3.7 Max · DTBench · Accuracy · % ↗
SciCode ↗49.54%
Qwen3.7 Max · SciCode · Score · % ↗
Text Arena (Coding) ↗1517.12 Elo
Qwen3.7 Max · WebDev Arena · Elo ↗
Epoch Capabilities Index (ECI) ↗154.04 ECI
Qwen3.7-Max · General ECI · 26 October 2026 fit ↗
Legal Research Bench ↗25.48 %
Qwen 3.7 Max · Legal Research Bench · All-Pass ↗
LegalBench ↗84.91 %
Qwen 3.7 Max · LegalBench · Accuracy ↗
Qwen 3.7 Max · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
Tax Agent Bench ↗15.83 %
Qwen 3.7 Max · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗47.78 %
Qwen 3.7 Max · Finance Agent v2 · Accuracy ↗
Qwen 3.7 Max · Excel Modeling Benchmark v1 · Accuracy ↗
CorpFin v2 ↗63.71 %
Qwen 3.7 Max · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗75.31 %
Qwen 3.7 Max · TaxEval · Accuracy ↗
MedCode ↗38.75 %
Qwen 3.7 Max · MedCode · Accuracy ↗
MedScribe ↗79.4 %
Qwen 3.7 Max · MedScribe · Accuracy ↗
MMLU-Pro ↗89.31 %
Qwen 3.7 Max · MMLU Pro · Accuracy ↗
Vibe Code Bench ↗47.67 %
Qwen 3.7 Max (OpenHands) · Vibe Code Bench · original task set ↗
Code Migration v1.1 ↗13.07 %
Qwen 3.7 Max · Code Migration v1 · Accuracy ↗
LiveCodeBench ↗87.06 %
Qwen 3.7 Max · LiveCodeBench · Accuracy ↗
DrugDiscoveryBench ↗29.30%
Qwen 3.7 Max (mini-SWE-agent) xhigh · DrugDiscoveryBench · Score ↗
ALE-Bench ↗1189.4 Performance points
qwen3.7-max · Average contest performance ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Kimi K2.6 →Kimi
21 of 28 shared benchmark comparisons
Gemini 3.6 Flash →Google
19 of 28 shared benchmark comparisons
GPT-5.4 →OpenAI
18 of 28 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Arena leaderboard — WebDev evaluation ↗
- EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗
- IFBench Benchmark | Artificial Analysis ↗
- ITBench-AA Benchmark | Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- 𝜏²-Bench Telecom Benchmark | Artificial Analysis ↗
- Terminal-Bench Hard Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- Ale Bench — methodology and published results ↗
- Chess Puzzles ↗
- CritPt v1 ↗
- Earthborne Rangers (EBR-bench) ↗
- FrontierMath Tier 4 (v2) ↗
- FrontierMath Tiers 1-3 (v2) ↗
- GPQA Diamond ↗
- Mystery Game Puzzles ↗
- OTIS Mock AIME 2024-2025 ↗
- SimpleQA Verified ↗
- SimpleBench ↗
- SWE-bench Verified ↗
- AI benchmarks & capabilities ↗
- Qwen3.7 Max — GBA Eval ↗
- DrugDiscoveryBench — evaluation methodology and results ↗
- ErdősBench: research mathematics, scoped progress and proof audits ↗
- Code Migration v1 — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- Excel Modeling Benchmark v1 — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- LiveCodeBench — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- ProofBench — evaluation methodology and results ↗
- SWE-bench Verified — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Qwen 3.7 Max · Qwen 3.7 Max (Mini-SWE-agent) · Qwen 3.7 Max (OpenHands) · Qwen 3.7 Max (mini-SWE-agent) xhigh · Qwen3.7 Max · Qwen3.7-Max · qwen3.7-max