Claude Opus 5 vs Grok 4.6
Claude Opus 5 
Grok 4.6 Verdict
- Claude Opus 5 leads on quality: 70.0 vs 63.8.
- Claude Opus 5 is stronger in agents & tools, coding, composite, human preference, maths, multimodal, reasoning.
- Grok 4.6 (medium) is stronger in knowledge, long context.
- Grok 4.6 (medium) is 3.3× cheaper ($3.00 vs $10.00 per 1M blended).
| Metric | Claude Opus 5 | Grok 4.6 (medium) |
|---|---|---|
| BenchLeader Index | 70.0 | 63.8 |
| Agents & tools score | 71.6 | – |
| Coding score | 74.4 | 63.9 |
| Composite score | 92.9 | 83.2 |
| Human preference score | 78.2 | – |
| Knowledge score | 70.5 | 77.3 |
| Long context score | 66.2 | 67.1 |
| Maths score | 67.1 | – |
| Multimodal score | 69.4 | – |
| Reasoning score | 71.1 | 62.1 |
| Blended price $/M | $10.00 | $3.00 |
| Output speed | 52 tok/s | 55 tok/s |
| Time to first answer | 81.6 s | 36.7 s |
| Context window | 1M | 500k |
| GPQA Diamond | 92.9% | – |
| OTIS Mock AIME | 97.8% | – |
| SimpleBench | 80.6% | – |
| SciCode | – | 54.6% |
| WeirdML | 86.3% | – |
| Epoch Capabilities Index | 162.6 | – |
| AA Intelligence Index | 50.7 | 43.0 |
| AA-LCR | 79.3% | 81.0% |
| MMMU-Pro | 84.7% | – |
| AA-Omniscience | 37.1 | 28 |
| GPQA Diamond (AA) | 93.2% | 93.5% |
| Humanity's Last Exam (AA) | 54.9% | 42.1% |
| SciCode (AA) | 56.4% | 55.9% |
| LiveCodeBench | 89.0% | – |
| MMLU-Pro | 91.6% | – |
| IOI | 91.7% | – |
| LegalBench | 87.0% | – |
| CorpFin | 73.2% | – |
| TaxEval | 75.1% | – |
| Terminal-Bench 2.1 (Vals) | 84.6% | – |
| SWE-bench (Vals) | 97.0% | – |
| GPQA Diamond (Vals) | 93.4% | – |
| Vals Index | 67.2 | – |
| HiL-Bench | 57.0% | – |
| EQ-Bench 4 | 1385 | – |
| ARC-AGI-1 | – | 87.5% |
| ARC-AGI-2 | – | 61.3% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.