Qwen 3.6 Plus vs MiMo V2.5: Benchmark Comparison
Qwen 3.6 Plus has the higher score on 14 of 18 shared benchmarks; MiMo V2.5 leads on 4.
The largest observed score gap is 22.23 pts on EMB , where MiMo V2.5 leads.
Reported ±1 standard-error ranges overlap on 5 of 18 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 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.25% ±0.83 | 1.67% ±0.00 | 0.42 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 14.90% ±2.48 | 9.13% ±2.00 | 5.77 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.23% ±0.42 | 78.89% ±0.51 | 5.35 pts | Reported ±1 SE ranges do not overlap |
| EMB | 32.87% ±2.81 | 55.09% ±3.13 | 22.23 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 40.85% ±0.13 | 36.73% ±0.11 | 4.12 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 67.97% ±0.91 | 59.26% ±0.98 | 8.71 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 32.84% ±2.75 | 29.16% ±2.71 | 3.68 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 74.73% ±0.85 | 71.83% ±0.88 | 2.90 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 36.89% ±2.02 | 31.89% ±2.02 | 5.00 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.96% ±1.92 | 72.15% ±1.85 | 4.81 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 87.37% ±1.67 | 81.57% ±2.05 | 5.81 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.67% ±0.32 | 82.93% ±0.37 | 4.74 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 84.16% ±0.88 | 80.00% ±0.96 | 4.16 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 44.86% ±3.43 | 43.27% ±3.39 | 1.59 pts | Reported ±1 SE ranges overlap |
| Code Migration | 11.10% ±1.31 | 14.23% ±3.69 | 3.13 pts | Reported ±1 SE ranges overlap |
| LiveCodeBench | 85.95% ±0.98 | 81.51% ±1.07 | 4.44 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 73.40% ±1.98 | 71.00% ±2.03 | 2.40 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 25.57% ±3.91 | 42.17% ±4.57 | 16.61 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.6 Plus average | MiMo V2.5 average |
|---|---|---|
| Legal | 33.46% | 29.90% |
| Finance | 49.85% | 50.41% |
| Healthcare | 56.93% | 52.02% |
| Academic | 86.40% | 81.50% |
| Education | 44.86% | 43.27% |
| Coding | 49.00% | 52.23% |
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 cost | Qwen 3.6 Plus latency | MiMo V2.5 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $3.94 | $0.04 | 14m48s | 6m59s |
| Legal Research Bench | $0.70 | $0.03 | 10m59s | 6m31s |
| LegalBench | N/A | N/A | 19.07s | 11.18s |
| EMB | $2.87 | $0.08 | 31m14s | 30m38s |
| Finance Agent (v2) | $0.81 | $0.09 | 10m12s | 5m39s |
| MortgageTax | N/A | N/A | 78.18s | 32.94s |
| Tax Agent Bench | $0.30 | $0.02 | 6m18s | 8m21s |
| TaxEval v2 | N/A | N/A | 70.63s | 26.30s |
| MedCode | N/A | N/A | 56.22s | 17.70s |
| MedScribe | N/A | N/A | 2m54s | 20.26s |
| GPQA Diamond | N/A | N/A | 2m02s | 89.39s |
| MMLU Pro | N/A | N/A | 46.18s | 30.25s |
| MMMU Pro | N/A | N/A | 111.94s | 42.47s |
| SAGE | N/A | N/A | 3m49s | 52.66s |
| Code Migration | $4.78 | $0.10 | 29m50s | 37m55s |
| LiveCodeBench | N/A | N/A | 7m56s | 108.61s |
| SWE-bench | $0.87 | $0.01 | 7m04s | 4m04s |
| Vibe Code Bench v1.1 | $5.45 | $0.07 | 38m10s | 26m20s |
Results available only for Qwen 3.6 Plus
- ProgramBench
Results available only for MiMo V2.5
- ProofBench v1.1