Qwen 3.6 Plus vs MiMo V2.5 Pro: Benchmark Comparison
Qwen 3.6 Plus has the higher score on 6 of 15 shared benchmarks; MiMo V2.5 Pro leads on 9.
The largest observed score gap is 22.36 pts on EMB , where MiMo V2.5 Pro 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 3.6 Plus | MiMo V2.5 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.25% ±0.83 | 2.08% ±0.83 | 0.83 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 14.90% ±2.48 | 15.87% ±2.54 | 0.96 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.23% ±0.42 | 77.13% ±0.55 | 7.10 pts | Reported ±1 SE ranges do not overlap |
| EMB | 32.87% ±2.81 | 55.23% ±3.11 | 22.36 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 40.85% ±0.13 | 41.50% ±1.19 | 0.66 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 32.84% ±2.75 | 34.79% ±2.62 | 1.94 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 74.73% ±0.85 | 73.79% ±0.86 | 0.94 pts | Reported ±1 SE ranges overlap |
| MedCode | 36.89% ±2.02 | 32.48% ±1.91 | 4.41 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.96% ±1.92 | 83.73% ±2.06 | 6.77 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 87.37% ±1.67 | 82.58% ±2.47 | 4.80 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.67% ±0.32 | 84.59% ±0.45 | 3.07 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 11.10% ±1.31 | 21.56% ±4.13 | 10.45 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 85.95% ±0.98 | 81.35% ±1.07 | 4.60 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 73.40% ±1.98 | 74.00% ±1.96 | 0.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 25.57% ±3.91 | 34.11% ±4.53 | 8.55 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.6 Plus average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 33.46% | 31.69% |
| Finance | 45.32% | 51.33% |
| Healthcare | 56.93% | 58.11% |
| Academic | 87.52% | 83.59% |
| Coding | 49.00% | 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 3.6 Plus cost | MiMo V2.5 Pro cost | Qwen 3.6 Plus latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $3.94 | $0.11 | 14m48s | 9m04s |
| Legal Research Bench | $0.70 | $0.08 | 10m59s | 6m56s |
| LegalBench | N/A | N/A | 19.07s | 27.14s |
| EMB | $2.87 | $0.22 | 31m14s | 29m08s |
| Finance Agent (v2) | $0.81 | $0.21 | 10m12s | 8m17s |
| Tax Agent Bench | $0.30 | $0.04 | 6m18s | 6m17s |
| TaxEval v2 | N/A | N/A | 70.63s | 62.83s |
| MedCode | N/A | N/A | 56.22s | 38.45s |
| MedScribe | N/A | N/A | 2m54s | 90.71s |
| GPQA Diamond | N/A | N/A | 2m02s | 4m11s |
| MMLU Pro | N/A | N/A | 46.18s | 67.76s |
| Code Migration | $4.78 | $0.24 | 29m50s | 48m53s |
| LiveCodeBench | N/A | N/A | 7m56s | 4m31s |
| SWE-bench | $0.87 | $0.02 | 7m04s | 7m51s |
| Vibe Code Bench v1.1 | $5.45 | $0.17 | 38m10s | 40m04s |
Results available only for Qwen 3.6 Plus
- MortgageTax
- MMMU Pro
- SAGE
- ProgramBench
Results available only for MiMo V2.5 Pro
- Vals Index
- ProofBench v1.1
- Terminal-Bench 4.0