Claude Opus 4.6 vs GPT-5.6 Terra
Claude Opus 4.6 
GPT-5.6 Terra Verdict
- GPT-5.6 Terra (xhigh) leads on quality: 64.2 vs 63.1.
- Claude Opus 4.6 is stronger in knowledge, multimodal, reasoning.
- GPT-5.6 Terra (xhigh) is stronger in agents & tools, coding, composite, human preference, 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 2.5× faster (93 vs 38 tokens per second).
| Metric | Claude Opus 4.6 | GPT-5.6 Terra (xhigh) |
|---|---|---|
| BenchLeader Index | 63.1 | 64.2 |
| Agents & tools score | 68.8 | 69.6 |
| Coding score | 62.3 | 63.7 |
| Composite score | 69.2 | 77.1 |
| Human preference score | 64.6 | 66.3 |
| Instruction following score | 53.7 | 65.0 |
| Knowledge score | 70.5 | 60.9 |
| Long context score | 65.5 | 66.0 |
| Maths score | 65.6 | 71.0 |
| Multimodal score | 63.6 | 63.0 |
| Reasoning score | 62.3 | 58.2 |
| Blended price $/M | $10.00 | $4.50 |
| Output speed | 38 tok/s | 93 tok/s |
| Time to first answer | 2.0 s | 32.5 s |
| Context window | 1M | 1M |
| GPQA Diamond | 90.5% | – |
| OTIS Mock AIME | 94.4% | – |
| SWE-bench Verified (Epoch) | 78.7% | – |
| Humanity's Last Exam | 19.0% | – |
| Terminal-Bench | 79.8% | – |
| SimpleBench | 67.6% | 48.9% |
| SciCode | – | 51.6% |
| Cybench | 93.0% | – |
| Remote Labor Index | 4.2% | – |
| WeirdML | 77.9% | – |
| APEX-Agents | 32.4% | – |
| FrontierCode | 26.6% | – |
| ProofBench | – | 74.0% |
| GSO-Bench | 33.3% | – |
| Epoch Capabilities Index | 155.3 | – |
| LMArena Text | 1498 | 1466 |
| LMArena Hard Prompts | 1527 | 1491 |
| LMArena Coding | 1546 | 1519 |
| LMArena WebDev | 1537 | 1521 |
| LMArena Vision | 1311 | 1269 |
| LMArena Agent | – | 1.5 |
| AA Intelligence Index | 31.9 | 38.2 |
| IFBench | 53.1% | 66.3% |
| AA-LCR | 78.0% | 79.0% |
| MMMU-Pro | 75.4% | 79.5% |
| AA-Omniscience | 13.7 | -3.0 |
| Terminal-Bench Hard | 48.5% | 62.9% |
| GPQA Diamond (AA) | 89.6% | 90.8% |
| Humanity's Last Exam (AA) | 39.9% | 41.9% |
| SciCode (AA) | – | 52.3% |
| τ²-Bench Telecom (AA) | 92.1% | 80.4% |
| LiveCodeBench | – | 85.9% |
| MMLU-Pro | – | 86.7% |
| IOI | – | 65.3% |
| CorpFin | – | 65.3% |
| TaxEval | – | 76.2% |
| GPQA Diamond (Vals) | – | 90.9% |
| HiL-Bench | 38.3% | – |
| EQ-Bench 4 | 1223 | – |
| Kagi LLM Benchmark | 72.4% | – |
| SWE-bench Verified (bash only) | 75.6% | – |
| SWE-bench Verified (any scaffold) | 75.6% | – |
| 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.