Claude Opus 5.5 vs GPT-6 Astra: Benchmark Comparison
Claude Opus 5.5 has the higher score on 21 of 29 shared benchmarks; GPT-6 Astra leads on 7.
The largest observed score gap is 26.88 pts on SWE-bench Multimodal , where Claude Opus 5.5 leads.
Reported ±1 standard-error ranges overlap on 10 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 Astra | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 70.14% ±1.00 | 65.02% ±1.10 | 5.12 pts | Reported ±1 SE ranges do not overlap |
| Vals RSI Index | 37.31% | 27.07% | 10.24 pts | Uncertainty comparison unavailable |
| Vals Finance Index | 65.34% ±1.48 | 55.64% ±1.38 | 9.70 pts | Reported ±1 SE ranges do not overlap |
| Vals Legal Index | 72.37% ±1.84 | 68.39% ±1.74 | 3.98 pts | Reported ±1 SE ranges do not overlap |
| Vals Science Index | 58.65% ±2.32 | 65.09% ±2.26 | 6.44 pts | Reported ±1 SE ranges do not overlap |
| HLAB-Vals-1.1 | 9.17% ±2.37 | 7.08% ±1.90 | 2.08 pts | Reported ±1 SE ranges overlap |
| Immigration | 72.14% ±1.45 | 67.69% ±1.55 | 4.45 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 50.48% ±3.48 | 39.42% ±3.40 | 11.06 pts | Reported ±1 SE ranges do not overlap |
| EMB v1.1 | 75.84% ±2.41 | 72.68% ±2.30 | 3.15 pts | Reported ±1 SE ranges overlap |
| Finance Agent v2.1 | 67.85% ±2.05 | 60.43% ±2.12 | 7.42 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 44.54% ±3.58 | 20.72% ±2.92 | 23.82 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 49.80% ±2.27 | 48.49% ±2.13 | 1.31 pts | Reported ±1 SE ranges overlap |
| MedScribe | 91.43% ±1.93 | 87.91% ±1.94 | 3.52 pts | Reported ±1 SE ranges 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 | 79.26% ±0.98 | 0.00 pts | Reported ±1 SE ranges overlap |
| MysteryMechanism | 49.55% ±3.36 | 53.15% ±3.36 | 3.60 pts | Reported ±1 SE ranges overlap |
| Robo-bench | 14.58% | 23.33% | 8.75 pts | Uncertainty comparison unavailable |
| Terminal-Bench-Science | 47.14% ±6.01 | 62.86% ±5.82 | 15.71 pts | Reported ±1 SE ranges do not overlap |
| Code Migration v1.1 | 81.01% ±3.21 | 80.58% ±2.34 | 0.43 pts | Reported ±1 SE ranges overlap |
| IOI | 95.06% ±4.94 | 100.00% ±0.00 | 4.94 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 18.50% ±2.75 | 5.50% ±1.62 | 13.00 pts | Reported ±1 SE ranges do not overlap |
| SWE-bench Multimodal | 70.21% ±2.09 | 43.33% ±2.26 | 26.88 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 65.15% ±0.00 | 59.60% ±4.40 | 5.56 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 90.29% ±1.53 | 89.59% ±2.17 | 0.70 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 55.36% ±5.13 | 41.07% ±2.56 | 14.28 pts | Reported ±1 SE ranges do not overlap |
| SRE Bench | 33.59% ±2.92 | 56.87% ±3.07 | 23.28 pts | Reported ±1 SE ranges do not overlap |
| Financial Coaching Bench | 76.16% ±1.52 | 67.53% ±1.69 | 8.63 pts | Reported ±1 SE ranges do not overlap |
| CUA-bench | 14.00% | 19.17% | 5.17 pts | Uncertainty comparison unavailable |
| Time Horizon Index: KSP | 91.33% ±0.00 | 90.50% ±0.00 | 0.83 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 5.5 average | GPT-6 Astra average |
|---|---|---|
| Legal | 43.93% | 38.07% |
| Finance | 62.74% | 51.28% |
| Healthcare | 70.61% | 68.20% |
| Math | 100.00% | 99.00% |
| Science | 47.63% | 54.65% |
| Coding | 70.04% | 63.10% |
| Cyber | 44.47% | 48.97% |
| Social Mobility | 76.16% | 67.53% |
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 Astra cost | Claude Opus 5.5 latency | GPT-6 Astra latency |
|---|---|---|---|---|
| Vals Index | $24.77 | $21.28 | 1h25m | 33m39s |
| Vals RSI Index | $411.86 | $759.51 | 90h00m | 90h00m |
| Vals Finance Index | $10.88 | $6.48 | 45m00s | 16m18s |
| Vals Legal Index | $19.94 | $13.94 | 1h19m | 24m08s |
| Vals Science Index | $8.71 | $8.03 | 59m51s | 40m37s |
| HLAB-Vals-1.1 | $21.81 | $25.46 | 58m27s | 32m33s |
| Immigration | $2.16 | $1.37 | 13m20s | 8m21s |
| Legal Research Bench | $23.61 | $10.58 | 1h52m | 24m51s |
| EMB v1.1 | $9.33 | $5.83 | 35m06s | 13m24s |
| Finance Agent v2.1 | $8.91 | $7.82 | 33m00s | 20m29s |
| Tax Agent Bench | $14.40 | $5.80 | 1h07m | 15m01s |
| MedCode | N/A | N/A | 4m07s | 102.86s |
| MedScribe | N/A | N/A | 7m22s | 2m34s |
| ProofBench v1.1 | $0.92 | $1.71 | 5m51s | 5m08s |
| BioMysteryBench | $2.95 | $1.72 | 12m19s | 4m46s |
| MysteryMechanism | $4.06 | $1.56 | 19m38s | 8m09s |
| Robo-bench | $11.38 | $28.48 | 2m07s | 74.88s |
| Terminal-Bench-Science | $19.12 | $20.80 | 2h28m | 1h49m |
| Code Migration v1.1 | $72.40 | $62.07 | 3h29m | 1h27m |
| IOI | $4.35 | $6.50 | 17m15s | 31m40s |
| ProgramBench | $42.66 | $11.57 | 2h24m | 27m02s |
| SWE-bench Multimodal | $3.63 | $1.81 | 18m32s | 7m03s |
| Terminal-Bench 4.0 | $12.04 | $9.58 | 1h04m | 35m42s |
| Vibe Code Bench v1.1 | $35.77 | $38.51 | 1h36m | 39m04s |
| CyberBench v1.1 | $2.85 | $1.84 | 18m11s | 4m10s |
| SRE Bench | $26.48 | $10.24 | 1h37m | 17m51s |
| Financial Coaching Bench | $1.63 | $1.72 | 10m52s | 12m33s |
| CUA-bench | $188.04 | $1821.37 | 14.71s | 32.09s |
| Time Horizon Index: KSP | $921.76 | $4206.59 | N/A | N/A |
Results available only for Claude Opus 5.5
- ClaimBench
- SAGE
- Vibe Code Bench 1-100 v1.1
- CyberOffense
- Access to Justice Benchmark
- Public Benefits Bench v1.1
Results available only for GPT-6 Astra
None.