Claude Opus 5.5 vs GPT-5.6 Sol: Benchmark Comparison
Claude Opus 5.5 has the higher score on 23 of 25 shared benchmarks; GPT-5.6 Sol leads on 2.
The largest observed score gap is 67.50 pts on Time Horizon Index: KSP , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 7 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 | GPT-5.6 Sol | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 66.97% ±0.89 | 58.01% ±1.02 | 8.97 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 23.88% | 13.43 pts | Uncertainty comparison unavailable |
| Harvey's Legal Agent Benchmark | 3.75% ±1.47 | 2.50% ±0.83 | 1.25 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 50.48% ±3.48 | 48.08% ±3.47 | 2.40 pts | Reported ±1 SE ranges overlap |
| EMB | 75.94% ±2.38 | 72.34% ±2.37 | 3.60 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 58.59% ±0.17 | 53.76% ±0.85 | 4.83 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 70.50% ±3.15 | 67.95% ±3.12 | 2.54 pts | Reported ±1 SE ranges overlap |
| MedCode | 49.80% ±2.27 | 43.97% ±2.26 | 5.82 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 91.43% ±1.93 | 85.23% ±1.97 | 6.20 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 100.00% ±0.00 | 83.00% ±3.77 | 17.00 pts | Reported ±1 SE ranges do not overlap |
| BioMysteryBench | 79.26% ±0.98 | 71.11% ±0.64 | 8.15 pts | Reported ±1 SE ranges do not overlap |
| MysteryMechanism | 49.55% ±3.36 | 33.33% ±3.17 | 16.22 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench Science | 47.14% ±6.01 | 20.00% ±4.82 | 27.14 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 45.83% ±3.36 | 52.56% ±3.42 | 6.73 pts | Reported ±1 SE ranges overlap |
| Code Migration | 66.65% ±4.33 | 52.92% ±4.35 | 13.73 pts | Reported ±1 SE ranges do not overlap |
| IOI | 95.06% ±4.94 | 91.17% ±4.51 | 3.89 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 18.50% ±2.75 | 1.50% ±0.86 | 17.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 37.88% ±0.00 | 27.27 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench 1-100 | 30.36% ±4.83 | 20.01% ±3.63 | 10.35 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 80.50% ±3.72 | 9.80 pts | Reported ±1 SE ranges do not overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 76.31% ±5.18 | 20.95 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 33.59% ±2.92 | 30.53% ±2.85 | 3.05 pts | Reported ±1 SE ranges overlap |
| Public Benefits Bench v1.1 | 70.64% ±1.19 | 66.51% ±1.23 | 4.13 pts | Reported ±1 SE ranges do not overlap |
| CUA-bench | 14.00% | 8.33% | 5.67 pts | Uncertainty comparison unavailable |
| Time Horizon Index: KSP | 91.33% ±0.00 | 23.83% ±0.00 | 67.50 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 5.5 average | GPT-5.6 Sol average |
|---|---|---|
| Legal | 27.12% | 25.29% |
| Finance | 68.34% | 64.68% |
| Healthcare | 70.61% | 64.60% |
| Math | 100.00% | 83.00% |
| Science | 58.65% | 41.48% |
| Education | 45.83% | 52.56% |
| Coding | 61.00% | 47.33% |
| Cyber | 44.47% | 53.42% |
| Social Mobility | 70.64% | 66.51% |
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-5.6 Sol cost | Claude Opus 5.5 latency | GPT-5.6 Sol latency |
|---|---|---|---|---|
| Vals Index | $32.14 | $14.24 | 1h19m | 37m23s |
| Vals RSI Index | $411.86 | $347.10 | 90h00m | 90h00m |
| Harvey's Legal Agent Benchmark | $21.38 | $10.37 | 49m00s | 22m50s |
| Legal Research Bench | $25.16 | $21.61 | 1h52m | 1h17m |
| EMB | $11.02 | $6.01 | 35m06s | 9m50s |
| Finance Agent (v2) | $9.22 | $1.25 | 33m08s | 19m25s |
| Tax Agent Bench | $15.09 | $7.51 | 1h07m | 44m41s |
| MedCode | N/A | N/A | 4m07s | 96.59s |
| MedScribe | N/A | N/A | 7m22s | 94.40s |
| ProofBench v1.1 | $0.96 | $1.44 | 5m51s | 8m40s |
| BioMysteryBench | $3.64 | $1.93 | 12m19s | 18m18s |
| MysteryMechanism | $4.62 | $0.96 | 19m38s | 8m43s |
| Terminal-Bench Science | $19.12 | $7.32 | 2h28m | 1h44m |
| SAGE | N/A | N/A | 114.20s | 75.39s |
| Code Migration | $112.97 | $24.54 | 3h19m | 59m12s |
| IOI | $5.26 | $7.98 | 17m15s | 1h02m |
| ProgramBench | $68.05 | $15.29 | 2h24m | 29m24s |
| Terminal-Bench 4.0 | $13.20 | $7.98 | 1h04m | 33m46s |
| Vibe Code Bench 1-100 | $44.12 | $47.43 | 2h28m | 2h37m |
| Vibe Code Bench v1.1 | $57.92 | $33.40 | 1h36m | 33m53s |
| CyberBench v1.1 | $3.48 | $3.05 | 18m11s | 10m47s |
| SRE Bench | $34.65 | $42.52 | 1h37m | 1h28m |
| Public Benefits Bench v1.1 | $5.95 | $8.85 | 1h20m | 1h01m |
| CUA-bench | $188.04 | $206.99 | 14.71s | 18.80s |
| Time Horizon Index: KSP | $1303.37 | $2027.20 | N/A | N/A |
Results available only for Claude Opus 5.5
None.
Results available only for GPT-5.6 Sol
- LegalBench
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SkillsBench
- SWE-bench