Qwen 3.7 Max vs MiniMax-M3: Benchmark Comparison
Qwen 3.7 Max has the higher score on 5 of 15 shared benchmarks; MiniMax-M3 leads on 10.
The largest observed score gap is 9.28 pts on EMB , where Qwen 3.7 Max leads.
Reported ±1 standard-error ranges overlap on 6 of 15 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.
Shared benchmark results
Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.
| Benchmark | Qwen 3.7 Max | MiniMax-M3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.67% ±0.83 | 4.17% ±1.65 | 2.50 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 25.48% ±3.03 | 29.81% ±3.18 | 4.33 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.91% ±0.41 | 85.42% ±0.44 | 0.50 pts | Reported ±1 SE ranges overlap |
| EMB | 57.04% ±2.85 | 47.76% ±2.95 | 9.28 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 47.78% ±0.73 | 48.27% ±0.44 | 0.49 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 47.41% ±3.24 | 49.69% ±3.25 | 2.28 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 75.31% ±0.84 | 72.73% ±0.86 | 2.58 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 38.75% ±2.20 | 46.29% ±2.10 | 7.54 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 79.40% ±1.91 | 87.25% ±1.96 | 7.86 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 90.15% ±1.50 | 92.68% ±1.44 | 2.52 pts | Reported ±1 SE ranges overlap |
| MMLU Pro | 89.31% ±0.30 | 84.22% ±0.36 | 5.09 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 13.07% ±2.86 | 19.93% ±3.94 | 6.86 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.06% ±0.97 | 82.15% ±1.05 | 4.90 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 68.80% ±2.07 | 75.00% ±1.94 | 6.20 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 47.67% ±4.63 | 47.57% ±5.44 | 0.10 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Qwen 3.7 Max average | MiniMax-M3 average |
|---|---|---|
| Legal | 37.35% | 39.80% |
| Finance | 56.88% | 54.61% |
| Healthcare | 59.07% | 66.77% |
| Academic | 89.73% | 88.45% |
| Coding | 54.15% | 56.16% |
Cost and latency
Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.
| Benchmark | Qwen 3.7 Max cost | MiniMax-M3 cost | Qwen 3.7 Max latency | MiniMax-M3 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $1.58 | $1.46 | 32m03s | 22m31s |
| Legal Research Bench | $1.40 | $0.34 | 13m29s | 13m34s |
| LegalBench | N/A | N/A | 11.85s | 8.21s |
| EMB | $2.86 | $2.09 | 32m37s | 31m30s |
| Finance Agent (v2) | $0.55 | $0.32 | 10m35s | 8m17s |
| Tax Agent Bench | $0.44 | $0.16 | 3m30s | 5m15s |
| TaxEval v2 | N/A | N/A | 57.68s | 94.04s |
| MedCode | N/A | N/A | 28.75s | 63.12s |
| MedScribe | N/A | N/A | 108.05s | 2m04s |
| GPQA Diamond | N/A | N/A | 2m07s | 4m39s |
| MMLU Pro | N/A | N/A | 29.15s | 41.39s |
| Code Migration | $1.93 | $7.07 | 25m32s | 1h14m |
| LiveCodeBench | N/A | N/A | 3m12s | 6m07s |
| SWE-bench | $3.23 | $0.42 | 16m16s | 12m06s |
| Vibe Code Bench v1.1 | $11.40 | $6.45 | 1h18m | 1h25m |
Results available only for Qwen 3.7 Max
None.
Results available only for MiniMax-M3
- Vals Index
- MortgageTax
- ProofBench v1.1
- MMMU Pro
- SAGE
- SkillsBench
- Terminal-Bench 4.0
- Vibe Code Bench 1-100
- CyberBench v1.1
- Public Benefits Bench v1.1