Claude Opus 5 vs GPT-5.6 Terra
Claude Opus 5 
GPT-5.6 Terra Verdict
- Claude Opus 5 leads on quality: 70.0 vs 64.2.
- Claude Opus 5 is stronger in agents & tools, coding, composite, human preference, knowledge, long context, multimodal, reasoning.
- GPT-5.6 Terra (xhigh) is stronger in maths, instruction following.
- GPT-5.6 Terra (xhigh) is 2.2× cheaper ($4.50 vs $10.00 per 1M blended).
- GPT-5.6 Terra (xhigh) streams 1.8× faster (93 vs 52 tokens per second).
| Metric | Claude Opus 5 | GPT-5.6 Terra (xhigh) |
|---|---|---|
| BenchLeader Index | 70.0 | 64.2 |
| Agents & tools score | 71.6 | 69.6 |
| Coding score | 74.4 | 63.7 |
| Composite score | 92.9 | 77.1 |
| Human preference score | 78.2 | 66.3 |
| Knowledge score | 70.5 | 60.9 |
| Long context score | 66.2 | 66.0 |
| Maths score | 67.1 | 71.0 |
| Multimodal score | 69.4 | 63.0 |
| Reasoning score | 71.1 | 58.2 |
| Instruction following score | – | 65.0 |
| Blended price $/M | $10.00 | $4.50 |
| Output speed | 52 tok/s | 93 tok/s |
| Time to first answer | 81.6 s | 32.5 s |
| Context window | 1M | 1M |
| GPQA Diamond | 92.9% | – |
| OTIS Mock AIME | 97.8% | – |
| SimpleBench | 80.6% | 48.9% |
| SciCode | – | 51.6% |
| WeirdML | 86.3% | – |
| ProofBench | – | 74.0% |
| Epoch Capabilities Index | 162.6 | – |
| LMArena Text | – | 1466 |
| LMArena Hard Prompts | – | 1491 |
| LMArena Coding | – | 1519 |
| LMArena WebDev | – | 1521 |
| LMArena Vision | – | 1269 |
| LMArena Agent | – | 1.5 |
| AA Intelligence Index | 50.7 | 38.2 |
| IFBench | – | 66.3% |
| AA-LCR | 79.3% | 79.0% |
| MMMU-Pro | 84.7% | 79.5% |
| AA-Omniscience | 37.1 | -3.0 |
| Terminal-Bench Hard | – | 62.9% |
| GPQA Diamond (AA) | 93.2% | 90.8% |
| Humanity's Last Exam (AA) | 54.9% | 41.9% |
| SciCode (AA) | 56.4% | 52.3% |
| τ²-Bench Telecom (AA) | – | 80.4% |
| LiveCodeBench | 89.0% | 85.9% |
| MMLU-Pro | 91.6% | 86.7% |
| IOI | 91.7% | 65.3% |
| LegalBench | 87.0% | – |
| CorpFin | 73.2% | 65.3% |
| TaxEval | 75.1% | 76.2% |
| Terminal-Bench 2.1 (Vals) | 84.6% | – |
| SWE-bench (Vals) | 97.0% | – |
| GPQA Diamond (Vals) | 93.4% | 90.9% |
| Vals Index | 67.2 | – |
| HiL-Bench | 57.0% | – |
| EQ-Bench 4 | 1385 | – |
| ARC-AGI-1 | – | 94.0% |
| ARC-AGI-2 | – | 74.2% |
| ARC-AGI-3 | – | 0.7% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.