Claude Opus 4.7 vs GPT 5.5: Benchmark Comparison
Claude Opus 4.7 has the higher score on 9 of 20 shared benchmarks; GPT 5.5 leads on 11.
The largest observed score gap is 5.76 pts on MedCode , where Claude Opus 4.7 leads.
Reported ±1 standard-error ranges overlap on 13 of 19 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 4.7 | GPT 5.5 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals RSI Index | 19.08% | 16.48% | 2.60 pts | Uncertainty comparison unavailable |
| Harvey's Legal Agent Benchmark | 6.67% ±2.00 | 3.75% ±1.17 | 2.92 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 38.46% ±3.38 | 40.38% ±3.41 | 1.92 pts | Reported ±1 SE ranges overlap |
| LegalBench | 85.25% ±0.45 | 86.52% ±0.41 | 1.26 pts | Reported ±1 SE ranges do not overlap |
| EMB | 63.73% ±3.11 | 64.54% ±2.87 | 0.82 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 51.51% ±0.49 | 51.76% ±0.55 | 0.25 pts | Reported ±1 SE ranges overlap |
| MortgageTax | 70.27% ±0.90 | 68.76% ±0.91 | 1.51 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 63.86% ±3.14 | 60.46% ±3.22 | 3.41 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 75.27% ±0.84 | 74.98% ±0.85 | 0.29 pts | Reported ±1 SE ranges overlap |
| MedCode | 54.86% ±2.21 | 49.10% ±2.19 | 5.76 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 82.95% ±1.98 | 86.87% ±1.93 | 3.91 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 90.15% ±1.54 | 93.18% ±1.29 | 3.03 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 89.87% ±0.30 | 88.14% ±0.32 | 1.73 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 85.55% ±0.84 | 88.27% ±0.77 | 2.72 pts | Reported ±1 SE ranges do not overlap |
| SAGE | 56.10% ±3.37 | 51.53% ±3.95 | 4.57 pts | Reported ±1 SE ranges overlap |
| Code Migration | 43.88% ±4.22 | 45.16% ±4.16 | 1.28 pts | Reported ±1 SE ranges overlap |
| LiveCodeBench | 85.07% ±1.01 | 85.30% ±1.02 | 0.22 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 0.00% ±0.00 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| SWE-bench | 82.00% ±1.72 | 82.60% ±1.70 | 0.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 71.00% ±4.51 | 69.85% ±4.54 | 1.16 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Opus 4.7 average | GPT 5.5 average |
|---|---|---|
| Legal | 43.46% | 43.55% |
| Finance | 64.93% | 64.10% |
| Healthcare | 68.91% | 67.98% |
| Academic | 88.52% | 89.86% |
| Education | 56.10% | 51.53% |
| Coding | 56.39% | 56.68% |
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 4.7 cost | GPT 5.5 cost | Claude Opus 4.7 latency | GPT 5.5 latency |
|---|---|---|---|---|
| Vals RSI Index | $1002.72 | $857.16 | 90h00m | 90h00m |
| Harvey's Legal Agent Benchmark | $10.81 | $4.60 | 24m44s | 12m14s |
| Legal Research Bench | $3.06 | $7.40 | 8m32s | 37m45s |
| LegalBench | N/A | N/A | 26.62s | 18.14s |
| EMB | $12.76 | $3.27 | 38m36s | 15m11s |
| Finance Agent (v2) | $4.03 | $4.15 | 6m00s | 11m02s |
| MortgageTax | N/A | N/A | 16.10s | 28.24s |
| Tax Agent Bench | $1.27 | $4.07 | 4m39s | 15m52s |
| TaxEval v2 | N/A | N/A | 62.07s | 95.83s |
| MedCode | N/A | N/A | 54.25s | 2m40s |
| MedScribe | N/A | N/A | 67.50s | 2m13s |
| GPQA Diamond | N/A | N/A | 3m23s | 112.33s |
| MMLU Pro | N/A | N/A | 3m08s | 42.11s |
| MMMU Pro | N/A | N/A | 70.80s | 54.15s |
| SAGE | N/A | N/A | 2m05s | 76.05s |
| Code Migration | $36.39 | $6.44 | 1h12m | 31m35s |
| LiveCodeBench | N/A | N/A | 7m42s | 2m47s |
| ProgramBench | N/A | N/A | 54m07s | 22m03s |
| SWE-bench | $2.42 | $1.36 | 7m22s | 7m06s |
| Vibe Code Bench v1.1 | $21.41 | $16.66 | 35m42s | 31m52s |
Results available only for Claude Opus 4.7
None.
Results available only for GPT 5.5
- SkillsBench
- SRE Bench
- Public Benefits Bench v1.1
- Time Horizon Index: KSP