Claude Opus 5.5 vs Wonder Full: Benchmark Comparison
Claude Opus 5.5 has the higher score on 22 of 30 shared benchmarks; Wonder Full leads on 8.
The largest observed score gap is 29.88 pts on CyberOffense , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 11 of 27 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 5.5 | Wonder Full | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 70.14% ±1.00 | 66.79% ±1.07 | 3.36 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 24.43% | 12.88 pts | Uncertainty comparison unavailable |
| Vals Finance Index | 65.34% ±1.48 | 64.55% ±1.40 | 0.79 pts | Reported ±1 SE ranges overlap |
| Vals Legal Index | 72.37% ±1.84 | 77.86% ±1.82 | 5.49 pts | Reported ±1 SE ranges do not overlap |
| Vals Science Index | 58.65% ±2.32 | 48.54% ±2.23 | 10.11 pts | Reported ±1 SE ranges do not overlap |
| HLAB-Vals-1.1 | 9.17% ±2.37 | 23.33% ±3.55 | 14.17 pts | Reported ±1 SE ranges do not overlap |
| Immigration | 72.14% ±1.45 | 71.22% ±1.46 | 0.92 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 50.48% ±3.48 | 53.37% ±3.47 | 2.88 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 75.84% ±2.41 | 75.00% ±2.14 | 0.84 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 67.85% ±2.05 | 67.58% ±1.98 | 0.27 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 44.54% ±3.58 | 43.00% ±3.57 | 1.54 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.80% ±2.27 | 49.93% ±2.18 | 0.14 pts | Reported ±1 SE ranges overlap |
| MedScribe | 91.43% ±1.93 | 89.33% ±2.00 | 2.10 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 |
| BioMysteryBench | 79.26% ±0.98 | 73.33% ±0.64 | 5.93 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 49.55% ±3.36 | 35.13% ±3.21 | 14.41 pts | Reported ±1 SE ranges do not overlap |
| Robo-bench | 14.58% | 10.42% | 4.17 pts | Uncertainty comparison unavailable |
| Terminal-Bench-Science | 47.14% ±6.01 | 37.14% ±5.82 | 10.00 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 81.01% ±3.21 | 62.79% ±3.17 | 18.22 pts | Reported ±1 SE ranges do not overlap |
| IOI | 95.06% ±4.94 | 79.83% ±2.99 | 15.22 pts | Reported ±1 SE ranges do not overlap |
| ProgramBench | 18.50% ±2.75 | 0.50% ±0.50 | 18.00 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 70.21% ±2.09 | 47.29% ±2.28 | 22.92 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 58.08% ±3.31 | 7.07 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 30.36% ±4.83 | 33.98% ±5.32 | 3.62 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 86.00% ±1.93 | 4.30 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 73.63% ±5.56 | 18.27 pts | Reported ±1 SE ranges do not overlap |
| CyberOffense | 77.10% | 47.22% | 29.88 pts | Uncertainty comparison unavailable |
| SRE Bench | 33.59% ±2.92 | 11.83% ±2.00 | 21.76 pts | Reported ±1 SE ranges do not overlap |
| Access to Justice Benchmark | 73.77% ±0.71 | 74.68% ±0.70 | 0.91 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 70.64% ±1.19 | 73.75% ±1.15 | 3.11 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 5.5 average | Wonder Full average |
|---|---|---|
| Legal | 43.93% | 49.31% |
| Finance | 62.74% | 61.86% |
| Healthcare | 70.61% | 69.63% |
| Math | 100.00% | 94.00% |
| Science | 47.63% | 39.01% |
| Coding | 64.37% | 52.64% |
| Cyber | 55.35% | 44.23% |
| Social Mobility | 72.20% | 74.21% |
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 5.5 cost | Wonder Full cost | Claude Opus 5.5 latency | Wonder Full latency |
|---|---|---|---|---|
| Vals Index | $24.77 | $6.81 | 1h25m | 59m19s |
| Vals RSI Index | N/A | N/A | 90h00m | 90h00m |
| Vals Finance Index | $10.88 | $3.14 | 45m00s | 20m06s |
| Vals Legal Index | $19.94 | $3.72 | 1h19m | 29m56s |
| Vals Science Index | $8.71 | $10.15 | 59m51s | 1h34m |
| HLAB-Vals-1.1 | $21.81 | $5.41 | 58m27s | 44m09s |
| Immigration | $2.16 | $0.39 | 13m20s | 9m12s |
| Legal Research Bench | $23.61 | $3.60 | 1h52m | 27m34s |
| EMB v1.1 | $9.33 | $4.58 | 35m06s | 28m05s |
| Finance Agent v2.1 | $8.91 | $2.68 | 33m00s | 14m10s |
| Tax Agent Bench | $14.40 | $2.15 | 1h07m | 18m04s |
| MedCode | N/A | N/A | 4m07s | 3m03s |
| MedScribe | N/A | N/A | 7m22s | 115.72s |
| ProofBench v1.1 | $0.92 | $0.86 | 5m51s | 11m36s |
| BioMysteryBench | $2.95 | $3.47 | 12m19s | 26m14s |
| MysteryMechanism | $4.06 | $4.16 | 19m38s | 41m34s |
| Robo-bench | $11.38 | $19.68 | 2m07s | 2m14s |
| Terminal-Bench-Science | $19.12 | $22.81 | 2h28m | 3h35m |
| Code Migration v1.1 | $72.40 | $23.58 | 3h29m | 4h18m |
| IOI | $4.35 | $7.08 | 17m15s | 1h31m |
| ProgramBench | $42.66 | $28.65 | 2h24m | 6h04m |
| SWE-bench Multimodal | $3.63 | $1.86 | 18m32s | 14m22s |
| Terminal-Bench 4.0 | $12.04 | $10.53 | 1h04m | 1h12m |
| Vibe Code Bench 1-100 | $44.12 | $19.54 | 2h28m | 1h57m |
| Vibe Code Bench v1.1 | $35.77 | $2.29 | 1h36m | 10m48s |
| CyberBench v1.1 | $2.85 | $3.63 | 18m11s | 35m27s |
| SRE Bench | $26.48 | $33.81 | 1h37m | 5h34m |
| Access to Justice Benchmark | $3.38 | $1.24 | 15m50s | 14m11s |
| Public Benefits Bench v1.1 | $5.29 | $4.64 | 1h20m | 1h13m |
Results available only for Claude Opus 5.5
- ClaimBench
- SAGE
- CUA-bench
- Time Horizon Index: KSP
Results available only for Wonder Full
- LegalBench