Qwen 3.6 Plus vs MiniMax-M3: Benchmark Comparison
Qwen 3.6 Plus has the higher score on 4 of 18 shared benchmarks; MiniMax-M3 leads on 14.
The largest observed score gap is 22.00 pts on Vibe Code Bench v1.1 , where MiniMax-M3 leads.
Reported ±1 standard-error ranges overlap on 3 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 | MiniMax-M3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.25% ±0.83 | 4.17% ±1.65 | 2.92 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 14.90% ±2.48 | 29.81% ±3.18 | 14.90 pts | Reported ±1 SE ranges do not overlap |
| LegalBench | 84.23% ±0.42 | 85.42% ±0.44 | 1.18 pts | Reported ±1 SE ranges do not overlap |
| EMB | 32.87% ±2.81 | 47.76% ±2.95 | 14.89 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 40.85% ±0.13 | 48.27% ±0.44 | 7.42 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 67.97% ±0.91 | 68.36% ±0.91 | 0.40 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 32.84% ±2.75 | 49.69% ±3.25 | 16.85 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 74.73% ±0.85 | 72.73% ±0.86 | 2.00 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 36.89% ±2.02 | 46.29% ±2.10 | 9.40 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.96% ±1.92 | 87.25% ±1.96 | 10.29 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 87.37% ±1.67 | 92.68% ±1.44 | 5.30 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.67% ±0.32 | 84.22% ±0.36 | 3.45 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 84.16% ±0.88 | 81.16% ±0.94 | 3.01 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 44.86% ±3.43 | 50.57% ±3.44 | 5.71 pts | Reported ±1 SE ranges overlap |
| Code Migration | 11.10% ±1.31 | 19.93% ±3.94 | 8.82 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 85.95% ±0.98 | 82.15% ±1.05 | 3.80 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 73.40% ±1.98 | 75.00% ±1.94 | 1.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 25.57% ±3.91 | 47.57% ±5.44 | 22.00 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.6 Plus average | MiniMax-M3 average |
|---|---|---|
| Legal | 33.46% | 39.80% |
| Finance | 49.85% | 57.36% |
| Healthcare | 56.93% | 66.77% |
| Academic | 86.40% | 86.02% |
| Education | 44.86% | 50.57% |
| Coding | 49.00% | 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 3.6 Plus cost | MiniMax-M3 cost | Qwen 3.6 Plus latency | MiniMax-M3 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $3.94 | $1.46 | 14m48s | 22m31s |
| Legal Research Bench | $0.70 | $0.34 | 10m59s | 13m34s |
| LegalBench | N/A | N/A | 19.07s | 8.21s |
| EMB | $2.87 | $2.09 | 31m14s | 31m30s |
| Finance Agent (v2) | $0.81 | $0.32 | 10m12s | 8m17s |
| MortgageTax | N/A | N/A | 78.18s | 26.76s |
| Tax Agent Bench | $0.30 | $0.16 | 6m18s | 5m15s |
| TaxEval v2 | N/A | N/A | 70.63s | 94.04s |
| MedCode | N/A | N/A | 56.22s | 63.12s |
| MedScribe | N/A | N/A | 2m54s | 2m04s |
| GPQA Diamond | N/A | N/A | 2m02s | 4m39s |
| MMLU Pro | N/A | N/A | 46.18s | 41.39s |
| MMMU Pro | N/A | N/A | 111.94s | 68.35s |
| SAGE | N/A | N/A | 3m49s | 118.54s |
| Code Migration | $4.78 | $7.07 | 29m50s | 1h14m |
| LiveCodeBench | N/A | N/A | 7m56s | 6m07s |
| SWE-bench | $0.87 | $0.42 | 7m04s | 12m06s |
| Vibe Code Bench v1.1 | $5.45 | $6.45 | 38m10s | 1h25m |
Results available only for Qwen 3.6 Plus
- ProgramBench
Results available only for MiniMax-M3
- Vals Index
- ProofBench v1.1
- SkillsBench
- Terminal-Bench 4.0
- Vibe Code Bench 1-100
- CyberBench v1.1
- Public Benefits Bench v1.1