Claude Fable 5.1 vs MiMo V2.6 Flash: Benchmark Comparison
Claude Fable 5.1 has the higher score on 18 of 20 shared benchmarks; MiMo V2.6 Flash leads on 2.
The largest observed score gap is 43.11 pts on IOI , where Claude Fable 5.1 leads.
Reported ±1 standard-error ranges overlap on 2 of 20 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 Fable 5.1 | MiMo V2.6 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 65.83% ±1.11 | 53.23% ±1.10 | 12.60 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 6.67% ±1.17 | 11.25% ±2.54 | 4.58 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 55.29% ±3.46 | 37.98% ±3.37 | 17.31 pts | Reported ±1 SE ranges do not overlap |
| EMB | 76.67% ±2.08 | 65.46% ±2.71 | 11.21 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 58.88% ±2.06 | 56.28% ±0.46 | 2.60 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 77.64% ±2.83 | 59.90% ±3.13 | 17.74 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 53.51% ±2.17 | 41.06% ±2.03 | 12.45 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 91.29% ±1.95 | 85.28% ±1.99 | 6.02 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 63.00% ±4.85 | 37.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 47.75% ±3.36 | 21.62% ±2.77 | 26.13 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 40.00% ±5.90 | 4.29% ±2.44 | 35.71 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 48.53% ±3.34 | 43.53% ±3.43 | 5.00 pts | Reported ±1 SE ranges overlap |
| Code Migration | 54.61% ±4.81 | 40.93% ±4.35 | 13.68 pts | Reported ±1 SE ranges do not overlap |
| IOI | 90.78% ±4.65 | 47.67% ±4.79 | 43.11 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 7.00% ±1.81 | 0.50% ±0.50 | 6.50 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 58.08% ±3.31 | 24.24% ±1.51 | 33.84 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.26% ±1.57 | 78.96% ±4.04 | 11.30 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 70.42% ±5.43 | 75.36% ±5.42 | 4.94 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 22.90% ±2.60 | 4.20% ±1.24 | 18.70 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 74.90% ±1.13 | 67.59% ±1.22 | 7.31 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Fable 5.1 average | MiMo V2.6 Flash average |
|---|---|---|
| Legal | 30.98% | 24.62% |
| Finance | 71.06% | 60.55% |
| Healthcare | 72.40% | 63.17% |
| Math | 100.00% | 63.00% |
| Science | 43.87% | 12.95% |
| Education | 48.53% | 43.53% |
| Coding | 60.15% | 38.46% |
| Cyber | 46.66% | 39.78% |
| Social Mobility | 74.90% | 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 Fable 5.1 cost | MiMo V2.6 Flash cost | Claude Fable 5.1 latency | MiMo V2.6 Flash latency |
|---|---|---|---|---|
| Vals Index | $28.71 | $0.20 | 1h17m | 58m02s |
| Harvey's Legal Agent Benchmark | $46.21 | $0.09 | 1h52m | 17m12s |
| Legal Research Bench | $23.06 | $0.07 | 57m29s | 15m20s |
| EMB | $15.93 | $0.11 | 29m32s | 25m22s |
| Finance Agent (v2) | $8.35 | $0.07 | 18m14s | 7m02s |
| Tax Agent Bench | $13.18 | $0.05 | 28m34s | 17m19s |
| MedCode | N/A | N/A | 3m35s | 93.37s |
| MedScribe | N/A | N/A | 3m08s | 74.48s |
| ProofBench v1.1 | $2.70 | $0.12 | 7m58s | 1h03m |
| MysteryMechanism | $5.63 | $0.06 | 17m41s | 35m08s |
| Terminal-Bench Science | $38.01 | $0.24 | 2h36m | 3h59m |
| SAGE | N/A | N/A | 105.75s | 2m16s |
| Code Migration | $70.97 | $0.49 | 4h20m | 3h12m |
| IOI | $11.20 | $0.22 | 30m06s | 1h49m |
| ProgramBench | $58.52 | $0.47 | 2h27m | 3h22m |
| Terminal-Bench 4.0 | $17.18 | $0.22 | 1h00m | 2h25m |
| Vibe Code Bench v1.1 | $33.37 | $0.56 | 57m40s | 50m13s |
| CyberBench v1.1 | $4.01 | $0.05 | 18m32s | 28m22s |
| SRE Bench | $32.23 | $0.40 | 2h03m | 3h22m |
| Public Benefits Bench v1.1 | $7.48 | $0.03 | 48m02s | 20m56s |
Results available only for Claude Fable 5.1
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SkillsBench
- Vibe Code Bench 1-100
- CUA-bench
- Time Horizon Index: KSP
Results available only for MiMo V2.6 Flash
- BioMysteryBench