Claude Opus 4.8 vs MiMo V2.6 Pro: Benchmark Comparison
Claude Opus 4.8 has the higher score on 6 of 15 shared benchmarks; MiMo V2.6 Pro leads on 9.
The largest observed score gap is 9.74 pts on SAGE , where Claude Opus 4.8 leads.
Reported ±1 standard-error ranges overlap on 10 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 | Claude Opus 4.8 | MiMo V2.6 Pro | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 55.10% ±1.01 | 55.20% ±1.18 | 0.10 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 9.58% ±2.15 | 10.83% ±2.45 | 1.25 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 43.75% ±3.45 | 47.12% ±3.47 | 3.37 pts | Reported ±1 SE ranges overlap |
| EMB | 69.37% ±2.61 | 62.86% ±3.14 | 6.52 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 53.92% ±0.16 | 57.34% ±0.57 | 3.42 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 64.91% ±3.17 | 64.94% ±3.21 | 0.03 pts | Reported ±1 SE ranges overlap |
| MedCode | 53.22% ±2.17 | 44.97% ±2.10 | 8.25 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 85.75% ±1.93 | 88.31% ±1.94 | 2.55 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench Science | 4.29% ±2.44 | 2.86% ±2.01 | 1.43 pts | Reported ±1 SE ranges overlap |
| SAGE | 54.79% ±3.35 | 45.05% ±3.40 | 9.74 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 47.25% ±4.18 | 43.01% ±4.32 | 4.24 pts | Reported ±1 SE ranges 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 | 31.31% ±3.07 | 8.08 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.72% ±3.08 | 85.22% ±3.39 | 2.50 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 68.13% ±1.21 | 68.94% ±1.20 | 0.81 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Opus 4.8 average | MiMo V2.6 Pro average |
|---|---|---|
| Legal | 26.67% | 28.97% |
| Finance | 62.73% | 61.71% |
| Healthcare | 69.49% | 66.64% |
| Science | 4.29% | 2.86% |
| Education | 54.79% | 45.05% |
| Coding | 38.55% | 40.01% |
| Social Mobility | 68.13% | 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 | Claude Opus 4.8 cost | MiMo V2.6 Pro cost | Claude Opus 4.8 latency | MiMo V2.6 Pro latency |
|---|---|---|---|---|
| Vals Index | $13.14 | $0.41 | 39m48s | 1h07m |
| Harvey's Legal Agent Benchmark | $10.22 | $0.22 | 24m08s | 25m49s |
| Legal Research Bench | $2.82 | $0.18 | 11m54s | 30m16s |
| EMB | $12.06 | $0.33 | 43m52s | 55m14s |
| Finance Agent (v2) | $4.22 | $0.20 | 9m07s | 10m48s |
| Tax Agent Bench | $1.69 | $0.13 | 7m59s | 25m48s |
| MedCode | N/A | N/A | 105.92s | 2m57s |
| MedScribe | N/A | N/A | 82.36s | 2m53s |
| Terminal-Bench Science | $23.14 | $0.62 | 1h55m | 3h12m |
| SAGE | N/A | N/A | 3m06s | 3m40s |
| Code Migration | $30.51 | $0.69 | 1h15m | 2h49m |
| ProgramBench | $31.27 | $0.73 | 1h32m | 3h00m |
| Terminal-Bench 4.0 | $17.14 | $0.50 | 1h11m | 2h42m |
| Vibe Code Bench v1.1 | $26.88 | $1.04 | 1h16m | 1h01m |
| Public Benefits Bench v1.1 | $1.89 | $0.08 | 12m48s | 37m14s |
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 Pro
- ProofBench v1.1
- MysteryMechanism
- IOI
- CyberBench v1.1
- SRE Bench