GPT-6 Sol vs MiMo V2.6 Pro: Benchmark Comparison
GPT-6 Sol has the higher score on 10 of 15 shared benchmarks; MiMo V2.6 Pro leads on 5.
The largest observed score gap is 43.28 pts on IOI , where GPT-6 Sol leads.
Reported ±1 standard-error ranges overlap on 4 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 | GPT-6 Sol | MiMo V2.6 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 28.85% ±3.15 | 47.12% ±3.47 | 18.27 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 15.00% ±2.58 | 32.39% ±3.36 | 17.39 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 47.07% ±2.12 | 44.97% ±2.10 | 2.10 pts | Reported ±1 SE ranges overlap |
| MedScribe | 82.03% ±1.94 | 88.31% ±1.94 | 6.27 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 83.00% ±3.77 | 70.00% ±4.61 | 13.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 30.18% ±3.09 | 15.31% ±2.42 | 14.87 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 30.00% ±5.52 | 2.86% ±2.01 | 27.14 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 44.79% ±3.36 | 45.05% ±3.40 | 0.26 pts | Reported ±1 SE ranges overlap |
| IOI | 82.61% ±9.24 | 39.33% ±2.41 | 43.28 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 2.00% ±0.99 | 0.50% ±0.50 | 1.50 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 44.44% ±3.54 | 31.31% ±3.07 | 13.13 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 87.82% ±2.53 | 85.22% ±3.39 | 2.60 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 77.98% ±5.11 | 72.86% ±5.50 | 5.12 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 30.53% ±2.85 | 3.05% ±1.06 | 27.48 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 56.63% ±1.29 | 68.94% ±1.20 | 12.31 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | GPT-6 Sol average | MiMo V2.6 Pro average |
|---|---|---|
| Legal | 28.85% | 47.12% |
| Finance | 15.00% | 32.39% |
| Healthcare | 64.55% | 66.64% |
| Math | 83.00% | 70.00% |
| Science | 30.09% | 9.09% |
| Education | 44.79% | 45.05% |
| Coding | 54.22% | 39.09% |
| Cyber | 54.25% | 37.95% |
| Social Mobility | 56.63% | 68.94% |
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 | GPT-6 Sol cost | MiMo V2.6 Pro cost | GPT-6 Sol latency | MiMo V2.6 Pro latency |
|---|---|---|---|---|
| Legal Research Bench | $4.90 | $0.18 | 24m09s | 30m16s |
| Tax Agent Bench | $2.28 | $0.13 | 17m32s | 25m48s |
| MedCode | N/A | N/A | 62.71s | 2m57s |
| MedScribe | N/A | N/A | 81.14s | 2m53s |
| ProofBench v1.1 | $0.48 | $0.25 | 5m05s | 1h02m |
| MysteryMechanism | $0.46 | $0.15 | 6m13s | 44m00s |
| Terminal-Bench-Science | $5.82 | $0.62 | 1h22m | 3h12m |
| SAGE | N/A | N/A | 31.42s | 3m40s |
| IOI | $2.70 | $0.84 | 30m38s | 2h26m |
| ProgramBench | $11.67 | $0.73 | 46m11s | 3h00m |
| Terminal-Bench 4.0 | $5.79 | $0.50 | 34m56s | 2h42m |
| Vibe Code Bench v1.1 | $26.36 | $1.04 | 38m56s | 1h01m |
| CyberBench v1.1 | $1.34 | $0.09 | 12m14s | 27m41s |
| SRE Bench | $20.65 | $0.53 | 1h03m | 2h23m |
| Public Benefits Bench v1.1 | $2.49 | $0.08 | 31m02s | 37m14s |
Results available only for GPT-6 Sol
- Vals RSI Index
- Vals Science Index
- BioMysteryBench
Results available only for MiMo V2.6 Pro
- Vals Finance Index
- Vals Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- Code Migration v1.1
- SWE-bench Multimodal