Claude Opus 4.7 vs GPT-5.6 Terra
Claude Opus 4.7 
GPT-5.6 Terra Verdict
- Claude Opus 4.7 leads on quality: 65.5 vs 64.2.
- Claude Opus 4.7 is stronger in coding, composite, human preference, knowledge, multimodal, reasoning.
- GPT-5.6 Terra (xhigh) is stronger in agents & tools, instruction following, long context, maths.
- GPT-5.6 Terra (xhigh) is 2.2× cheaper ($4.50 vs $10.00 per 1M blended).
- GPT-5.6 Terra (xhigh) streams 2.0× faster (93 vs 46 tokens per second).
| Metric | Claude Opus 4.7 | GPT-5.6 Terra (xhigh) |
|---|---|---|
| BenchLeader Index | 65.5 | 64.2 |
| Agents & tools score | 69.4 | 69.6 |
| Coding score | 64.8 | 63.7 |
| Composite score | 80.3 | 77.1 |
| Human preference score | 68.8 | 66.3 |
| Instruction following score | 58.5 | 65.0 |
| Knowledge score | 66.4 | 60.9 |
| Long context score | 65.9 | 66.0 |
| Maths score | 65.2 | 71.0 |
| Multimodal score | 65.7 | 63.0 |
| Reasoning score | 66.3 | 58.2 |
| Blended price $/M | $10.00 | $4.50 |
| Output speed | 46 tok/s | 93 tok/s |
| Time to first answer | 21.2 s | 32.5 s |
| Context window | 1M | 1M |
| Humanity's Last Exam | 36.2% | – |
| Terminal-Bench | 80.2% | – |
| SimpleBench | 61.7% | 48.9% |
| SciCode | – | 51.6% |
| WeirdML | 76.4% | – |
| FrontierCode | 38.5% | – |
| ProofBench | – | 74.0% |
| GSO-Bench | 44.1% | – |
| Epoch Capabilities Index | 156.3 | – |
| LMArena Text | 1495 | 1466 |
| LMArena Hard Prompts | 1519 | 1491 |
| LMArena Coding | 1547 | 1519 |
| LMArena WebDev | 1557 | 1521 |
| LMArena Vision | 1317 | 1269 |
| LMArena Agent | – | 1.5 |
| AA Intelligence Index | 40.7 | 38.2 |
| IFBench | 58.6% | 66.3% |
| AA-LCR | 78.7% | 79.0% |
| MMMU-Pro | 78.8% | 79.5% |
| AA-Omniscience | 27.3 | -3.0 |
| Terminal-Bench Hard | 51.5% | 62.9% |
| GPQA Diamond (AA) | 91.4% | 90.8% |
| Humanity's Last Exam (AA) | 42.3% | 41.9% |
| SciCode (AA) | – | 52.3% |
| τ²-Bench Telecom (AA) | 88.6% | 80.4% |
| AIME (Vals) | 96.3% | – |
| LiveCodeBench | 85.1% | 85.9% |
| MMLU-Pro | 89.9% | 86.7% |
| IOI | 47.1% | 65.3% |
| LegalBench | 85.3% | – |
| CorpFin | 66.1% | 65.3% |
| TaxEval | 75.3% | 76.2% |
| Terminal-Bench 2.1 (Vals) | 68.5% | – |
| SWE-bench (Vals) | 82.0% | – |
| GPQA Diamond (Vals) | 90.2% | 90.9% |
| Vals Index | 56.1 | – |
| HiL-Bench | 41.7% | – |
| EQ-Bench 4 | 1311 | – |
| Kagi LLM Benchmark | 73.3% | – |
| 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.