Claude Opus 4.8 vs Gemini 3.1 Pro
Claude Opus 4.8 
Gemini 3.1 Pro Verdict
- Claude Opus 4.8 and Gemini 3.1 Pro are level on quality (64.7 vs 63.9).
- Claude Opus 4.8 is stronger in agents & tools, coding, composite, human preference, knowledge.
- Gemini 3.1 Pro is stronger in instruction following, long context, multimodal, reasoning, maths.
- Gemini 3.1 Pro is 2.2× cheaper ($4.50 vs $10.00 per 1M blended).
- Gemini 3.1 Pro streams 1.9× faster (110 vs 58 tokens per second).
| Metric | Claude Opus 4.8 | Gemini 3.1 Pro |
|---|---|---|
| BenchLeader Index | 64.7 | 63.9 |
| Agents & tools score | 65.0 | 63.7 |
| Coding score | 65.7 | 59.8 |
| Composite score | 81.9 | 67.2 |
| Human preference score | 65.6 | 59.6 |
| Instruction following score | 61.6 | 69.5 |
| Knowledge score | 66.3 | 66.1 |
| Long context score | 65.3 | 67.6 |
| Multimodal score | 64.4 | 66.1 |
| Reasoning score | 64.2 | 69.5 |
| Maths score | – | 60.7 |
| Blended price $/M | $10.00 | $4.50 |
| Output speed | 58 tok/s | 110 tok/s |
| Time to first answer | 29.5 s | 30.5 s |
| Context window | 1M | 1.0M |
| GPQA Diamond | – | 94.1% |
| FrontierMath Tiers 1–3 | – | 59.6% |
| FrontierMath Tier 4 | – | 26.8% |
| OTIS Mock AIME | – | 95.6% |
| Humanity's Last Exam | – | 46.4% |
| Terminal-Bench | – | 80.2% |
| SimpleBench | 64.8% | 79.6% |
| SciCode | – | 58.9% |
| Remote Labor Index | 8.3% | – |
| WeirdML | – | 72.1% |
| APEX-Agents | – | 33.5% |
| FrontierCode | 46.5% | – |
| ProofBench | – | 26.0% |
| GSO-Bench | 47.1% | 22.6% |
| Epoch Capabilities Index | 158.3 | 155 |
| LMArena Text | 1473 | 1487 |
| LMArena Hard Prompts | 1503 | 1507 |
| LMArena Coding | 1527 | 1521 |
| LMArena WebDev | 1540 | 1447 |
| LMArena Vision | 1289 | 1295 |
| LMArena Agent | – | -5.3 |
| AA Intelligence Index | 42.0 | 30.4 |
| IFBench | 62.2% | 77.1% |
| AA-LCR | 77.7% | 82.0% |
| MMMU-Pro | – | 82.4% |
| AA-Omniscience | 28.8 | 31.9 |
| Terminal-Bench Hard | 58.3% | 53.8% |
| GPQA Diamond (AA) | 92.0% | 94.1% |
| Humanity's Last Exam (AA) | 48.7% | 47.0% |
| SciCode (AA) | 54.4% | 58.7% |
| τ²-Bench Telecom (AA) | 94.4% | 95.6% |
| LiveCodeBench | 87.8% | – |
| MMLU-Pro | 89.6% | – |
| LegalBench | 83.6% | – |
| CorpFin | 66.7% | – |
| TaxEval | 75.6% | – |
| Terminal-Bench 2.1 (Vals) | 71.9% | – |
| SWE-bench (Vals) | 88.6% | – |
| GPQA Diamond (Vals) | 92.4% | – |
| Vals Index | 60.9 | – |
| AIME 2026 | – | 98.3% |
| HMMT February 2026 | – | 94.7% |
| MathArena Apex | – | 60.9% |
| MultiChallenge | – | 71.4% |
| PRBench Finance | – | 41.9% |
| PRBench Legal | – | 44.0% |
| MultiNRC | – | 64.7% |
| HiL-Bench | 35.3% | 35.3% |
| TutorBench | – | 53.0% |
| EQ-Bench 4 | 1281 | 1142 |
| ARC-AGI-1 | – | 98.0% |
| ARC-AGI-2 | – | 77.1% |
| ARC-AGI-3 | – | 0.4% |
Data as of 2026-09-09. Best configuration of each model; every score links to its source on the model pages.