Claude Fable 5.1 vs Wonder Full: Benchmark Comparison
Claude Fable 5.1 has the higher score on 16 of 20 shared benchmarks; Wonder Full leads on 3.
The largest observed score gap is 13.96 pts on SWE-bench Multimodal , where Claude Fable 5.1 leads.
Reported ±1 standard-error ranges overlap on 10 of 18 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 Full | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals RSI Index | 36.09% | 24.43% | 11.66 pts | Uncertainty comparison unavailable |
| Legal Research Bench | 55.29% ±3.46 | 53.37% ±3.47 | 1.92 pts | Reported ±1 SE ranges overlap |
| LegalBench | 88.51% ±0.42 | 87.42% ±0.41 | 1.09 pts | Reported ±1 SE ranges do not overlap |
| EMB v1.1 | 76.73% ±2.13 | 75.00% ±2.14 | 1.73 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 49.19% ±3.61 | 43.00% ±3.57 | 6.20 pts | Reported ±1 SE ranges overlap |
| MedCode | 53.51% ±2.17 | 49.93% ±2.18 | 3.58 pts | Reported ±1 SE ranges overlap |
| MedScribe | 91.29% ±1.95 | 89.33% ±2.00 | 1.96 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 94.00% ±2.39 | 6.00 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 47.75% ±3.36 | 35.13% ±3.21 | 12.61 pts | Reported ±1 SE ranges do not overlap |
| Robo-bench | 5.83% | 10.42% | 4.58 pts | Uncertainty comparison unavailable |
| Terminal-Bench-Science | 40.00% ±5.90 | 37.14% ±5.82 | 2.86 pts | Reported ±1 SE ranges overlap |
| IOI | 90.78% ±4.65 | 79.83% ±2.99 | 10.95 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 |
| SWE-bench Multimodal | 61.25% ±2.23 | 47.29% ±2.28 | 13.96 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 58.08% ±3.31 | 58.08% ±3.31 | 0.00 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench 1-100 | 28.00% ±4.49 | 33.98% ±5.32 | 5.98 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 90.26% ±1.57 | 86.00% ±1.93 | 4.27 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 70.42% ±5.43 | 73.63% ±5.56 | 3.22 pts | Reported ±1 SE ranges overlap |
| SRE Bench | 22.90% ±2.60 | 11.83% ±2.00 | 11.07 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 74.90% ±1.13 | 73.75% ±1.15 | 1.15 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Fable 5.1 average | Wonder Full average |
|---|---|---|
| Legal | 71.90% | 70.39% |
| Finance | 62.96% | 59.00% |
| Healthcare | 72.40% | 69.63% |
| Math | 100.00% | 94.00% |
| Science | 31.19% | 27.56% |
| Coding | 55.90% | 50.95% |
| Cyber | 46.66% | 42.73% |
| Social Mobility | 74.90% | 73.75% |
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 Full cost | Claude Fable 5.1 latency | Wonder Full latency |
|---|---|---|---|---|
| Vals RSI Index | N/A | N/A | 90h00m | 90h00m |
| Legal Research Bench | $23.06 | $3.60 | 57m29s | 27m34s |
| LegalBench | N/A | N/A | 12.40s | 38.27s |
| EMB v1.1 | $15.93 | $4.58 | 29m32s | 28m05s |
| Tax Agent Bench | $13.18 | $2.15 | 28m34s | 18m04s |
| MedCode | N/A | N/A | 3m35s | 3m03s |
| MedScribe | N/A | N/A | 3m08s | 115.72s |
| ProofBench v1.1 | $2.70 | $0.86 | 7m58s | 11m36s |
| MysteryMechanism | $5.63 | $4.16 | 17m41s | 41m34s |
| Robo-bench | $20.40 | $19.68 | 2m04s | 2m14s |
| Terminal-Bench-Science | $38.01 | $22.81 | 2h36m | 3h35m |
| IOI | $11.20 | $7.08 | 30m06s | 1h31m |
| ProgramBench | $58.52 | $28.65 | 2h27m | 6h04m |
| SWE-bench Multimodal | $5.46 | $1.86 | 15m12s | 14m22s |
| Terminal-Bench 4.0 | $17.18 | $10.53 | 1h00m | 1h12m |
| Vibe Code Bench 1-100 | $149.66 | $19.54 | 2h53m | 1h57m |
| Vibe Code Bench v1.1 | $33.37 | $2.29 | 57m40s | 10m48s |
| CyberBench v1.1 | $4.01 | $3.63 | 18m32s | 35m27s |
| SRE Bench | $32.23 | $33.81 | 2h03m | 5h34m |
| Public Benefits Bench v1.1 | $7.48 | $4.64 | 48m02s | 1h13m |
Results available only for Claude Fable 5.1
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- SkillsBench
- CUA-bench
- Time Horizon Index: KSP
Results available only for Wonder Full
- Vals Finance Index
- Vals Index
- Vals Legal Index
- Vals Science Index
- HLAB-Vals-1.1
- Finance Agent v2.1
- BioMysteryBench
- Code Migration v1.1