Claude Opus 5.5 vs GPT-6.1 Sol: Benchmark Comparison
Claude Opus 5.5 has the higher score on 20 of 28 shared benchmarks; GPT-6.1 Sol leads on 7.
The largest observed score gap is 26.67 pts on SWE-bench Multimodal , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 13 of 26 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 | GPT-6.1 Sol | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Finance Index | 65.59% ±1.48 | 55.81% ±1.50 | 9.78 pts | Reported ±1 SE ranges do not overlap |
| Vals Index | 70.18% ±1.00 | 63.94% ±1.07 | 6.23 pts | Reported ±1 SE ranges do not overlap |
| Vals Legal Index | 72.33% ±1.84 | 68.72% ±1.77 | 3.62 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 26.62% | 10.69 pts | Uncertainty comparison unavailable |
| Vals Science Index | 58.65% ±2.32 | 59.63% ±2.31 | 0.98 pts | Reported ±1 SE ranges overlap |
| HLAB-Vals-1.1 | 9.17% ±2.37 | 6.25% ±1.83 | 2.92 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 50.48% ±3.48 | 38.46% ±3.38 | 12.02 pts | Reported ±1 SE ranges do not overlap |
| ClaimBench | 100.00% ±0.00 | 100.00% ±0.00 | 0.00 pts | Reported ±1 SE ranges overlap |
| EMB v1.1 | 75.84% ±2.41 | 71.09% ±2.75 | 4.75 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 67.85% ±2.05 | 61.82% ±2.11 | 6.03 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 45.57% ±3.59 | 21.75% ±2.98 | 23.82 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 49.80% ±2.27 | 48.84% ±2.12 | 0.96 pts | Reported ±1 SE ranges overlap |
| MedScribe | 91.43% ±1.93 | 86.45% ±1.90 | 4.98 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 99.00% ±1.00 | 1.00 pts | Reported ±1 SE ranges overlap |
| BioMysteryBench | 79.26% ±0.98 | 79.63% ±0.74 | 0.37 pts | Reported ±1 SE ranges overlap |
| MysteryMechanism | 49.55% ±3.36 | 46.40% ±3.35 | 3.15 pts | Reported ±1 SE ranges overlap |
| Robo-bench | 14.58% | 28.33% | 13.75 pts | Uncertainty comparison unavailable |
| Terminal-Bench-Science | 47.14% ±6.01 | 52.86% ±6.01 | 5.71 pts | Reported ±1 SE ranges overlap |
| SAGE | 45.83% ±3.36 | 46.54% ±3.46 | 0.71 pts | Reported ±1 SE ranges overlap |
| Code Migration v1.1 | 81.01% ±3.21 | 77.32% ±2.98 | 3.69 pts | Reported ±1 SE ranges overlap |
| IOI | 95.06% ±4.94 | 96.89% ±3.11 | 1.83 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 18.50% ±2.75 | 3.00% ±1.21 | 15.50 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 70.21% ±2.09 | 43.54% ±2.27 | 26.67 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 55.05% ±1.82 | 10.10 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 88.93% ±1.89 | 1.36 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 39.29% ±2.74 | 16.07 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 33.59% ±2.92 | 50.76% ±3.10 | 17.17 pts | Reported ±1 SE ranges do not overlap |
| Public Benefits Bench v1.1 | 70.64% ±1.19 | 59.34% ±1.28 | 11.30 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 5.5 average | GPT-6.1 Sol average |
|---|---|---|
| Legal | 29.82% | 22.36% |
| Finance | 72.31% | 63.66% |
| Healthcare | 70.61% | 67.65% |
| Math | 100.00% | 99.00% |
| Science | 47.63% | 51.80% |
| Education | 45.83% | 46.54% |
| Coding | 70.04% | 60.79% |
| Cyber | 44.47% | 45.02% |
| Social Mobility | 70.64% | 59.34% |
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 | GPT-6.1 Sol cost | Claude Opus 5.5 latency | GPT-6.1 Sol latency |
|---|---|---|---|---|
| Vals Finance Index | $11.67 | $1.36 | 45m00s | 19m16s |
| Vals Index | $28.12 | $3.61 | 1h25m | 44m24s |
| Vals Legal Index | $20.54 | $2.75 | 1h19m | 31m40s |
| Vals RSI Index | $411.86 | $98.21 | 90h00m | 90h00m |
| Vals Science Index | $9.13 | $1.36 | 59m51s | 33m11s |
| HLAB-Vals-1.1 | $21.38 | $3.54 | 58m27s | 40m26s |
| Legal Research Bench | $25.16 | $3.38 | 1h52m | 34m20s |
| ClaimBench | $0.091833 | $0.029239 | 6.47s | 11.26s |
| EMB v1.1 | $11.02 | $1.14 | 35m06s | 18m28s |
| Finance Agent v2.1 | $8.91 | $1.63 | 33m00s | 19m05s |
| Tax Agent Bench | $15.09 | $1.32 | 1h07m | 20m14s |
| MedCode | N/A | N/A | 4m07s | 115.34s |
| MedScribe | N/A | N/A | 7m22s | 2m50s |
| ProofBench v1.1 | $0.96 | $0.23 | 5m51s | 4m45s |
| BioMysteryBench | $3.64 | $0.37 | 12m19s | 8m51s |
| MysteryMechanism | $4.62 | $0.28 | 19m38s | 7m17s |
| Robo-bench | $11.38 | $4.97 | 2m07s | 79.89s |
| Terminal-Bench-Science | $19.12 | $3.44 | 2h28m | 1h23m |
| SAGE | N/A | N/A | 114.20s | 50.22s |
| Code Migration v1.1 | $72.40 | $9.51 | 3h29m | 1h39m |
| IOI | $5.26 | $1.26 | 17m15s | 31m31s |
| ProgramBench | $68.05 | $2.87 | 2h24m | 1h10m |
| SWE-bench Multimodal | $4.92 | $0.35 | 18m32s | 6m56s |
| Terminal-Bench 4.0 | $13.20 | $1.72 | 1h04m | 45m12s |
| Vibe Code Bench v1.1 | $57.92 | $6.23 | 1h36m | 1h15m |
| CyberBench v1.1 | $3.48 | $0.29 | 18m11s | 3m42s |
| SRE Bench | $34.65 | $2.69 | 1h37m | 32m32s |
| Public Benefits Bench v1.1 | $5.95 | $0.69 | 1h20m | 50m24s |
Results available only for Claude Opus 5.5
- Vibe Code Bench 1-100
- CUA-bench
- Time Horizon Index: KSP
Results available only for GPT-6.1 Sol
None.