Claude Opus 5.5 vs Wonder: Benchmark Comparison
Claude Opus 5.5 has the higher score on 20 of 24 shared benchmarks; Wonder leads on 3.
The largest observed score gap is 28.11 pts on IOI , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 8 of 23 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 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 70.14% ±1.00 | 64.88% ±1.07 | 5.27 pts | Reported ±1 SE ranges do not overlap |
| Vals Finance Index | 65.34% ±1.48 | 61.23% ±1.46 | 4.12 pts | Reported ±1 SE ranges do not overlap |
| Vals Legal Index | 72.37% ±1.84 | 75.26% ±1.83 | 2.89 pts | Reported ±1 SE ranges overlap |
| Vals Science Index | 58.65% ±2.32 | 39.12% ±1.96 | 19.53 pts | Reported ±1 SE ranges do not overlap |
| HLAB-Vals-1.1 | 9.17% ±2.37 | 23.75% ±3.65 | 14.58 pts | Reported ±1 SE ranges do not overlap |
| Immigration | 72.14% ±1.45 | 69.62% ±1.44 | 2.52 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 50.48% ±3.48 | 50.48% ±3.48 | 0.00 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 75.84% ±2.41 | 72.50% ±2.41 | 3.33 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 67.85% ±2.05 | 65.55% ±2.03 | 2.30 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 44.54% ±3.58 | 36.27% ±3.47 | 8.27 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 |
| BioMysteryBench | 79.26% ±0.98 | 67.04% ±0.37 | 12.22 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 49.55% ±3.36 | 27.48% ±3.00 | 22.07 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench-Science | 47.14% ±6.01 | 22.86% ±5.05 | 24.29 pts | Reported ±1 SE ranges do not overlap |
| Code Migration v1.1 | 81.01% ±3.21 | 72.36% ±3.19 | 8.66 pts | Reported ±1 SE ranges do not overlap |
| IOI | 95.06% ±4.94 | 66.94% ±4.91 | 28.11 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 70.21% ±2.09 | 45.63% ±2.28 | 24.58 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 49.49% ±2.20 | 15.66 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 30.36% ±4.83 | 26.55% ±4.33 | 3.81 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 83.09% ±2.49 | 7.20 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 80.36% ±5.13 | 25.00 pts | Reported ±1 SE ranges do not overlap |
| Access to Justice Benchmark | 73.77% ±0.71 | 72.96% ±0.72 | 0.81 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 70.64% ±1.19 | 70.23% ±1.19 | 0.41 pts | Reported ±1 SE ranges overlap |
| CUA-bench | 14.00% | 7.17% | 6.83 pts | Uncertainty comparison unavailable |
Performance by category
| Category | Claude Opus 5.5 average | Wonder average |
|---|---|---|
| Legal | 43.93% | 47.95% |
| Finance | 62.74% | 58.11% |
| Math | 100.00% | 84.00% |
| Science | 58.65% | 39.12% |
| Coding | 72.01% | 57.34% |
| Cyber | 55.36% | 80.36% |
| Social Mobility | 72.20% | 71.59% |
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 Opus 5.5 cost | Wonder cost | Claude Opus 5.5 latency | Wonder latency |
|---|---|---|---|---|
| Vals Index | $24.77 | $10.65 | 1h25m | 35m24s |
| Vals Finance Index | $10.88 | $3.37 | 45m00s | 10m12s |
| Vals Legal Index | $19.94 | $4.32 | 1h19m | 12m55s |
| Vals Science Index | $8.71 | $8.74 | 59m51s | 43m08s |
| HLAB-Vals-1.1 | $21.81 | $7.08 | 58m27s | 15m06s |
| Immigration | $2.16 | $0.30 | 13m20s | 2m53s |
| Legal Research Bench | $23.61 | $3.98 | 1h52m | 15m27s |
| EMB v1.1 | $9.33 | $5.60 | 35m06s | 17m14s |
| Finance Agent v2.1 | $8.91 | $2.62 | 33m00s | 5m10s |
| Tax Agent Bench | $14.40 | $1.88 | 1h07m | 8m13s |
| ProofBench v1.1 | $0.92 | $1.31 | 5m51s | 15m29s |
| BioMysteryBench | $2.95 | $3.23 | 12m19s | 18m02s |
| MysteryMechanism | $4.06 | $3.39 | 19m38s | 18m17s |
| Terminal-Bench-Science | $19.12 | $19.61 | 2h28m | 1h33m |
| Code Migration v1.1 | $72.40 | $47.93 | 3h29m | 2h42m |
| IOI | $4.35 | $4.54 | 17m15s | 25m02s |
| SWE-bench Multimodal | $3.63 | $1.70 | 18m32s | 9m44s |
| Terminal-Bench 4.0 | $12.04 | $14.66 | 1h04m | 54m41s |
| Vibe Code Bench 1-100 | $44.12 | $13.72 | 2h28m | 31m08s |
| Vibe Code Bench v1.1 | $35.77 | $1.80 | 1h36m | 5m50s |
| CyberBench v1.1 | $2.85 | $3.66 | 18m11s | 13m45s |
| Access to Justice Benchmark | $3.38 | $1.10 | 15m50s | 4m46s |
| Public Benefits Bench v1.1 | $5.29 | $2.46 | 1h20m | 19m44s |
| CUA-bench | $188.04 | $597.21 | 14.71s | 30.56s |
Results available only for Claude Opus 5.5
- Vals RSI Index
- ClaimBench
- MedCode
- MedScribe
- Robo-bench
- SAGE
- ProgramBench
- CyberOffense
- SRE Bench
- Time Horizon Index: KSP
Results available only for Wonder
None.