Qwen 3.7 Max vs Kimi K2.6: Benchmark Comparison
Qwen 3.7 Max has the higher score on 10 of 15 shared benchmarks; Kimi K2.6 leads on 4.
The largest observed score gap is 14.70 pts on Code Migration , where Kimi K2.6 leads.
Reported ±1 standard-error ranges overlap on 9 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 | Kimi K2.6 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 1.67% ±0.83 | 1.67% ±0.83 | 0.00 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 | 84.74% ±0.45 | 0.17 pts | Reported ±1 SE ranges overlap |
| EMB | 57.04% ±2.85 | 57.85% ±2.74 | 0.81 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 47.78% ±0.73 | 44.90% ±0.73 | 2.88 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 47.41% ±3.24 | 45.13% ±3.23 | 2.27 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 75.31% ±0.84 | 74.65% ±0.85 | 0.65 pts | Reported ±1 SE ranges overlap |
| MedCode | 38.75% ±2.20 | 40.14% ±2.04 | 1.39 pts | Reported ±1 SE ranges overlap |
| MedScribe | 79.40% ±1.91 | 78.15% ±1.79 | 1.25 pts | Reported ±1 SE ranges overlap |
| GPQA Diamond | 90.15% ±1.50 | 89.14% ±2.00 | 1.01 pts | Reported ±1 SE ranges overlap |
| MMLU Pro | 89.31% ±0.30 | 87.57% ±0.33 | 1.74 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 13.07% ±2.86 | 27.77% ±4.14 | 14.70 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 87.06% ±0.97 | 86.77% ±0.97 | 0.29 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 68.80% ±2.07 | 76.20% ±1.91 | 7.40 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 47.67% ±4.63 | 37.89% ±4.91 | 9.78 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.7 Max average | Kimi K2.6 average |
|---|---|---|
| Legal | 37.35% | 34.09% |
| Finance | 56.88% | 55.64% |
| Healthcare | 59.07% | 59.15% |
| Academic | 89.73% | 88.36% |
| Coding | 54.15% | 57.16% |
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 | Kimi K2.6 cost | Qwen 3.7 Max latency | Kimi K2.6 latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $1.58 | $0.82 | 32m03s | 23m23s |
| Legal Research Bench | $1.40 | $1.52 | 13m29s | 30m53s |
| LegalBench | N/A | N/A | 11.85s | 50.07s |
| EMB | $2.86 | $2.20 | 32m37s | 39m48s |
| Finance Agent (v2) | $0.55 | $1.14 | 10m35s | 27m10s |
| Tax Agent Bench | $0.44 | $0.57 | 3m30s | 15m24s |
| TaxEval v2 | N/A | N/A | 57.68s | 4m27s |
| MedCode | N/A | N/A | 28.75s | 5m05s |
| MedScribe | N/A | N/A | 108.05s | 8m14s |
| GPQA Diamond | N/A | N/A | 2m07s | 9m05s |
| MMLU Pro | N/A | N/A | 29.15s | 2m36s |
| Code Migration | $1.93 | $5.11 | 25m32s | 1h30m |
| LiveCodeBench | N/A | N/A | 3m12s | 8m49s |
| SWE-bench | $3.23 | $0.27 | 16m16s | 8m40s |
| Vibe Code Bench v1.1 | $11.40 | $1.93 | 1h18m | 49m28s |
Results available only for Qwen 3.7 Max
None.
Results available only for Kimi K2.6
- MortgageTax
- MMMU Pro
- SAGE
- ProgramBench
- Public Benefits Bench v1.1