Qwen 3.7 Max vs MiMo V2.5 Pro: Benchmark Comparison
Qwen 3.7 Max has the higher score on 11 of 15 shared benchmarks; MiMo V2.5 Pro leads on 4.
The largest observed score gap is 13.56 pts on Vibe Code Bench v1.1 , where Qwen 3.7 Max leads.
Reported ±1 standard-error ranges overlap on 3 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 | MiMo V2.5 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.67% ±0.83 | 2.08% ±0.83 | 0.42 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 25.48% ±3.03 | 15.87% ±2.54 | 9.62 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.91% ±0.41 | 77.13% ±0.55 | 7.78 pts | Reported ±1 SE ranges do not overlap |
| EMB | 57.04% ±2.85 | 55.23% ±3.11 | 1.81 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 47.78% ±0.73 | 41.50% ±1.19 | 6.27 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 47.41% ±3.24 | 34.79% ±2.62 | 12.62 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 75.31% ±0.84 | 73.79% ±0.86 | 1.51 pts | Reported ±1 SE ranges overlap |
| MedCode | 38.75% ±2.20 | 32.48% ±1.91 | 6.27 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 79.40% ±1.91 | 83.73% ±2.06 | 4.33 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 90.15% ±1.50 | 82.58% ±2.47 | 7.58 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.31% ±0.30 | 84.59% ±0.45 | 4.72 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 13.07% ±2.86 | 21.56% ±4.13 | 8.49 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.06% ±0.97 | 81.35% ±1.07 | 5.70 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 68.80% ±2.07 | 74.00% ±1.96 | 5.20 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 47.67% ±4.63 | 34.11% ±4.53 | 13.56 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.7 Max average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 37.35% | 31.69% |
| Finance | 56.88% | 51.33% |
| Healthcare | 59.07% | 58.11% |
| Academic | 89.73% | 83.59% |
| Coding | 54.15% | 52.76% |
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 | MiMo V2.5 Pro cost | Qwen 3.7 Max latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $1.58 | $0.11 | 32m03s | 9m04s |
| Legal Research Bench | $1.40 | $0.08 | 13m29s | 6m56s |
| LegalBench | N/A | N/A | 11.85s | 27.14s |
| EMB | $2.86 | $0.22 | 32m37s | 29m08s |
| Finance Agent (v2) | $0.55 | $0.21 | 10m35s | 8m17s |
| Tax Agent Bench | $0.44 | $0.04 | 3m30s | 6m17s |
| TaxEval v2 | N/A | N/A | 57.68s | 62.83s |
| MedCode | N/A | N/A | 28.75s | 38.45s |
| MedScribe | N/A | N/A | 108.05s | 90.71s |
| GPQA Diamond | N/A | N/A | 2m07s | 4m11s |
| MMLU Pro | N/A | N/A | 29.15s | 67.76s |
| Code Migration | $1.93 | $0.24 | 25m32s | 48m53s |
| LiveCodeBench | N/A | N/A | 3m12s | 4m31s |
| SWE-bench | $3.23 | $0.02 | 16m16s | 7m51s |
| Vibe Code Bench v1.1 | $11.40 | $0.17 | 1h18m | 40m04s |
Results available only for Qwen 3.7 Max
None.
Results available only for MiMo V2.5 Pro
- Vals Index
- ProofBench v1.1
- Terminal-Bench 4.0