Claude Fable 5.1 vs Wonder: Benchmark Comparison
Claude Fable 5.1 has the higher score on 13 of 14 shared benchmarks; Wonder leads on 1.
The largest observed score gap is 23.83 pts on IOI , where Claude Fable 5.1 leads.
Reported ±1 standard-error ranges overlap on 4 of 13 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 | Wonder | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 55.29% ±3.46 | 50.48% ±3.48 | 4.81 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 76.73% ±2.13 | 72.50% ±2.41 | 4.22 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 49.19% ±3.61 | 36.27% ±3.47 | 12.93 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 84.00% ±3.69 | 16.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 47.75% ±3.36 | 27.48% ±3.00 | 20.27 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 40.00% ±5.90 | 22.86% ±5.05 | 17.14 pts | Reported ±1 SE ranges do not overlap |
| IOI | 90.78% ±4.65 | 66.94% ±4.91 | 23.83 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 61.25% ±2.23 | 45.63% ±2.28 | 15.63 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 58.08% ±3.31 | 49.49% ±2.20 | 8.59 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 28.00% ±4.49 | 26.55% ±4.33 | 1.45 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 90.26% ±1.57 | 83.09% ±2.49 | 7.17 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 70.42% ±5.43 | 80.36% ±5.13 | 9.94 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 74.90% ±1.13 | 70.23% ±1.19 | 4.67 pts | Reported ±1 SE ranges do not overlap |
| CUA-bench | 13.17% | 7.17% | 6.00 pts | Uncertainty comparison unavailable |
Performance by category
| Category | Claude Fable 5.1 average | Wonder average |
|---|---|---|
| Legal | 55.29% | 50.48% |
| Finance | 62.96% | 54.39% |
| Math | 100.00% | 84.00% |
| Science | 43.87% | 25.17% |
| Coding | 65.67% | 54.34% |
| Cyber | 70.42% | 80.36% |
| Social Mobility | 74.90% | 70.23% |
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 | Wonder cost | Claude Fable 5.1 latency | Wonder latency |
|---|---|---|---|---|
| Legal Research Bench | $23.06 | $3.98 | 57m29s | 15m27s |
| EMB v1.1 | $15.93 | $5.60 | 29m32s | 17m14s |
| Tax Agent Bench | $13.18 | $1.88 | 28m34s | 8m13s |
| ProofBench v1.1 | $2.70 | $1.31 | 7m58s | 15m29s |
| MysteryMechanism | $5.63 | $3.39 | 17m41s | 18m17s |
| Terminal-Bench-Science | $38.01 | $19.61 | 2h36m | 1h33m |
| IOI | $11.20 | $4.54 | 30m06s | 25m02s |
| SWE-bench Multimodal | $5.46 | $1.70 | 15m12s | 9m44s |
| Terminal-Bench 4.0 | $17.18 | $14.66 | 1h00m | 54m41s |
| Vibe Code Bench 1-100 | $149.66 | $13.72 | 2h53m | 31m08s |
| Vibe Code Bench v1.1 | $33.37 | $1.80 | 57m40s | 5m50s |
| CyberBench v1.1 | $4.01 | $3.66 | 18m32s | 13m45s |
| Public Benefits Bench v1.1 | $7.48 | $2.46 | 48m02s | 19m44s |
| CUA-bench | $323.78 | $597.21 | 37.44s | 30.56s |
Results available only for Claude Fable 5.1
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- MedCode
- MedScribe
- Robo-bench
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- ProgramBench
- SkillsBench
- SRE Bench
- Time Horizon Index: KSP
Results available only for Wonder
- Vals Finance Index
- Vals Index
- Vals Legal Index
- Vals Science Index
- HLAB-Vals-1.1
- Finance Agent v2.1
- BioMysteryBench
- Code Migration v1.1