Kimi K2.6 vs MiMo V2.5 Pro: Benchmark Comparison
Kimi K2.6 has the higher score on 12 of 15 shared benchmarks; MiMo V2.5 Pro leads on 2.
The largest observed score gap is 10.35 pts on Tax Agent Bench , where Kimi K2.6 leads.
Reported ±1 standard-error ranges overlap on 7 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 | Kimi K2.6 | 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 | 15.87% ±2.54 | 15.87% ±2.54 | 0.00 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.74% ±0.45 | 77.13% ±0.55 | 7.61 pts | Reported ±1 SE ranges do not overlap |
| EMB | 57.85% ±2.74 | 55.23% ±3.11 | 2.63 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 44.90% ±0.73 | 41.50% ±1.19 | 3.40 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 45.13% ±3.23 | 34.79% ±2.62 | 10.35 pts | Reported ±1 SE ranges do not overlap |
| TaxEval v2 | 74.65% ±0.85 | 73.79% ±0.86 | 0.86 pts | Reported ±1 SE ranges overlap |
| MedCode | 40.14% ±2.04 | 32.48% ±1.91 | 7.66 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 78.15% ±1.79 | 83.73% ±2.06 | 5.58 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 89.14% ±2.00 | 82.58% ±2.47 | 6.57 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.57% ±0.33 | 84.59% ±0.45 | 2.98 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 27.77% ±4.14 | 21.56% ±4.13 | 6.21 pts | Reported ±1 SE ranges overlap |
| LiveCodeBench | 86.77% ±0.97 | 81.35% ±1.07 | 5.42 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench | 76.20% ±1.91 | 74.00% ±1.96 | 2.20 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 37.89% ±4.91 | 34.11% ±4.53 | 3.78 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Kimi K2.6 average | MiMo V2.5 Pro average |
|---|---|---|
| Legal | 34.09% | 31.69% |
| Finance | 55.64% | 51.33% |
| Healthcare | 59.15% | 58.11% |
| Academic | 88.36% | 83.59% |
| Coding | 57.16% | 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 | Kimi K2.6 cost | MiMo V2.5 Pro cost | Kimi K2.6 latency | MiMo V2.5 Pro latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $0.82 | $0.11 | 23m23s | 9m04s |
| Legal Research Bench | $1.52 | $0.08 | 30m53s | 6m56s |
| LegalBench | N/A | N/A | 50.07s | 27.14s |
| EMB | $2.20 | $0.22 | 39m48s | 29m08s |
| Finance Agent (v2) | $1.14 | $0.21 | 27m10s | 8m17s |
| Tax Agent Bench | $0.57 | $0.04 | 15m24s | 6m17s |
| TaxEval v2 | N/A | N/A | 4m27s | 62.83s |
| MedCode | N/A | N/A | 5m05s | 38.45s |
| MedScribe | N/A | N/A | 8m14s | 90.71s |
| GPQA Diamond | N/A | N/A | 9m05s | 4m11s |
| MMLU Pro | N/A | N/A | 2m36s | 67.76s |
| Code Migration | $5.11 | $0.24 | 1h30m | 48m53s |
| LiveCodeBench | N/A | N/A | 8m49s | 4m31s |
| SWE-bench | $0.27 | $0.02 | 8m40s | 7m51s |
| Vibe Code Bench v1.1 | $1.93 | $0.17 | 49m28s | 40m04s |
Results available only for Kimi K2.6
- MortgageTax
- MMMU Pro
- SAGE
- ProgramBench
- Public Benefits Bench v1.1
Results available only for MiMo V2.5 Pro
- Vals Index
- ProofBench v1.1
- Terminal-Bench 4.0