Claude Opus 4.7 vs GPT-6 Luna: Benchmark Comparison
Claude Opus 4.7 has the higher score on 7 of 11 shared benchmarks; GPT-6 Luna leads on 4.
The largest observed score gap is 10.65 pts on Vibe Code Bench v1.1 , where GPT-6 Luna leads.
Reported ±1 standard-error ranges overlap on 5 of 11 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-6 Luna | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 6.67% ±2.00 | 2.92% ±1.36 | 3.75 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 38.46% ±3.38 | 30.29% ±3.19 | 8.17 pts | Reported ±1 SE ranges do not overlap |
| EMB | 63.73% ±3.11 | 68.52% ±2.81 | 4.79 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 51.51% ±0.49 | 49.87% ±0.23 | 1.64 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 63.86% ±3.14 | 58.86% ±3.21 | 5.00 pts | Reported ±1 SE ranges overlap |
| MedCode | 54.86% ±2.21 | 44.69% ±2.30 | 10.17 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 82.95% ±1.98 | 83.71% ±1.95 | 0.76 pts | Reported ±1 SE ranges overlap |
| SAGE | 56.10% ±3.37 | 48.09% ±3.38 | 8.01 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 43.88% ±4.22 | 42.55% ±4.42 | 1.32 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 0.00% ±0.00 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 71.00% ±4.51 | 81.65% ±3.38 | 10.65 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 4.7 average | GPT-6 Luna average |
|---|---|---|
| Legal | 22.56% | 16.60% |
| Finance | 59.70% | 59.08% |
| Healthcare | 68.91% | 64.20% |
| Education | 56.10% | 48.09% |
| Coding | 38.29% | 41.57% |
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-6 Luna cost | Claude Opus 4.7 latency | GPT-6 Luna latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $10.81 | $0.30 | 24m44s | 17m32s |
| Legal Research Bench | $3.06 | $0.44 | 8m32s | 42m28s |
| EMB | $12.76 | $0.14 | 38m36s | 17m21s |
| Finance Agent (v2) | $4.03 | $0.12 | 6m00s | 14m58s |
| Tax Agent Bench | $1.27 | $0.19 | 4m39s | 33m16s |
| MedCode | N/A | N/A | 54.25s | 108.77s |
| MedScribe | N/A | N/A | 67.50s | 2m50s |
| SAGE | N/A | N/A | 2m05s | 91.07s |
| Code Migration | $36.39 | $0.60 | 1h12m | 50m23s |
| ProgramBench | N/A | N/A | 54m07s | 28m55s |
| Vibe Code Bench v1.1 | $21.41 | $1.35 | 35m42s | 37m00s |
Results available only for Claude Opus 4.7
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SWE-bench
Results available only for GPT-6 Luna
- Vals Index
- ProofBench v1.1
- BioMysteryBench
- MysteryMechanism
- Terminal-Bench Science
- IOI
- Terminal-Bench 4.0
- CyberBench v1.1
- Public Benefits Bench v1.1