Claude Opus 4.8 vs MiMo V2.6 Flash: Benchmark Comparison
Claude Opus 4.8 has the higher score on 8 of 10 shared benchmarks; MiMo V2.6 Flash leads on 1.
The largest observed score gap is 12.16 pts on MedCode , where Claude Opus 4.8 leads.
Reported ±1 standard-error ranges overlap on 8 of 10 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 | Claude Opus 4.8 | MiMo V2.6 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 43.75% ±3.45 | 37.98% ±3.37 | 5.77 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 30.00% ±3.30 | 28.51% ±3.14 | 1.49 pts | Reported ±1 SE ranges overlap |
| MedCode | 53.22% ±2.17 | 41.06% ±2.03 | 12.16 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 85.75% ±1.93 | 85.28% ±1.99 | 0.48 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 4.29% ±2.44 | 4.29% ±2.44 | 0.00 pts | Reported ±1 SE ranges overlap |
| SAGE | 54.79% ±3.35 | 43.53% ±3.43 | 11.26 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 1.00% ±0.70 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 23.23% ±1.34 | 24.24% ±1.51 | 1.01 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 82.72% ±3.08 | 78.96% ±4.04 | 3.77 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 68.13% ±1.21 | 67.59% ±1.22 | 0.54 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Opus 4.8 average | MiMo V2.6 Flash average |
|---|---|---|
| Legal | 43.75% | 37.98% |
| Finance | 30.00% | 28.51% |
| Healthcare | 69.49% | 63.17% |
| Science | 4.29% | 4.29% |
| Education | 54.79% | 43.53% |
| Coding | 35.65% | 34.57% |
| Social Mobility | 68.13% | 67.59% |
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 | Claude Opus 4.8 cost | MiMo V2.6 Flash cost | Claude Opus 4.8 latency | MiMo V2.6 Flash latency |
|---|---|---|---|---|
| Legal Research Bench | $2.82 | $0.07 | 11m54s | 15m20s |
| Tax Agent Bench | $1.69 | $0.05 | 7m59s | 17m19s |
| MedCode | N/A | N/A | 105.92s | 93.37s |
| MedScribe | N/A | N/A | 82.36s | 74.48s |
| Terminal-Bench-Science | $23.14 | $0.24 | 1h55m | 3h59m |
| SAGE | N/A | N/A | 3m06s | 2m16s |
| ProgramBench | $31.27 | $0.47 | 1h32m | 3h22m |
| Terminal-Bench 4.0 | $17.14 | $0.22 | 1h11m | 2h25m |
| Vibe Code Bench v1.1 | $26.88 | $0.56 | 1h16m | 50m13s |
| Public Benefits Bench v1.1 | $1.89 | $0.03 | 12m48s | 20m56s |
Results available only for Claude Opus 4.8
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench
- Time Horizon Index: KSP
Results available only for MiMo V2.6 Flash
- Vals Finance Index
- Vals Index
- Vals Legal Index
- Vals Science Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- ProofBench v1.1
- BioMysteryBench
- MysteryMechanism
- Code Migration v1.1
- IOI
- CyberBench v1.1
- SRE Bench