Claude Opus 4.5 vs Gemini 3.1 Pro
Claude Opus 4.5 
Gemini 3.1 Pro Verdict
- Gemini 3.1 Pro leads on quality: 64.0 vs 60.7.
- Claude Opus 4.5 (thinking) is stronger in agents & tools, maths.
- Gemini 3.1 Pro is stronger in coding, composite, instruction following, knowledge, long context, multimodal, reasoning, human preference.
- Gemini 3.1 Pro is 2.2× cheaper ($4.50 vs $10.00 per 1M blended).
- Gemini 3.1 Pro streams 2.4× faster (108 vs 45 tokens per second).
| Metric | Claude Opus 4.5 (thinking) | Gemini 3.1 Pro |
|---|---|---|
| BenchLeader Index | 60.7 | 64.0 |
| Agents & tools score | 74.6 | 63.7 |
| Coding score | 56.4 | 59.9 |
| Composite score | 65.8 | 67.4 |
| Instruction following score | 54.8 | 69.6 |
| Knowledge score | 61.0 | 66.2 |
| Long context score | 65.2 | 67.6 |
| Maths score | 64.0 | 60.7 |
| Multimodal score | 58.0 | 66.2 |
| Reasoning score | 58.6 | 69.8 |
| Human preference score | – | 59.9 |
| Blended price $/M | $10.00 | $4.50 |
| Output speed | 45 tok/s | 108 tok/s |
| Time to first answer | 17.3 s | 30.5 s |
| Context window | 200k | 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 | – | 79.6% |
| SciCode | – | 58.9% |
| WeirdML | – | 72.1% |
| APEX-Agents | – | 33.5% |
| ProofBench | – | 26.0% |
| GSO-Bench | – | 22.6% |
| Epoch Capabilities Index | – | 155 |
| LMArena Text | – | 1487 |
| LMArena Hard Prompts | – | 1507 |
| LMArena Coding | – | 1521 |
| LMArena WebDev | – | 1447 |
| LMArena Vision | – | 1295 |
| LMArena Agent | – | -5.3 |
| AA Intelligence Index | 29.1 | 30.4 |
| IFBench | 58.0% | 77.1% |
| AA-LCR | 77.3% | 82.0% |
| MMMU-Pro | 74.0% | 82.4% |
| AA-Omniscience | 14 | 31.9 |
| Terminal-Bench Hard | 47.0% | 53.8% |
| GPQA Diamond (AA) | 86.6% | 94.1% |
| Humanity's Last Exam (AA) | 30.1% | 47.0% |
| SciCode (AA) | – | 58.7% |
| τ²-Bench Telecom (AA) | 89.5% | 95.6% |
| AIME (Vals) | 95.4% | – |
| LiveCodeBench | 83.7% | – |
| MMLU-Pro | 87.3% | – |
| IOI | 20.3% | – |
| LegalBench | 84.6% | – |
| CorpFin | 65.1% | – |
| TaxEval | 74.9% | – |
| MedQA | 95.9% | – |
| MGSM | 95.2% | – |
| SWE-bench (Vals) | 76.4% | – |
| GPQA Diamond (Vals) | 85.9% | – |
| AIME 2026 | – | 98.3% |
| HMMT February 2026 | – | 94.7% |
| MathArena Apex | – | 60.9% |
| MultiChallenge | 59.0% | 71.4% |
| PRBench Finance | 46.2% | 41.9% |
| PRBench Legal | 44.2% | 44.0% |
| VISTA | 46.4% | – |
| MultiNRC | 48.6% | 64.7% |
| HiL-Bench | – | 35.3% |
| TutorBench | 51.2% | 53.0% |
| EQ-Bench 4 | – | 1142 |
| Kagi LLM Benchmark | 80.2% | – |
| ARC-AGI-1 | 80.0% | 98.0% |
| ARC-AGI-2 | 37.6% | 77.1% |
| ARC-AGI-3 | – | 0.4% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Opus 4.5 vs Gemini 3.1 Pro: questions
- Is Claude Opus 4.5 better than Gemini 3.1 Pro?
- Gemini 3.1 Pro leads on quality: 64.0 vs 60.7. The BenchLeader Index combines every independent quality benchmark; Gemini 3.1 Pro is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Opus 4.5 better than Gemini 3.1 Pro for coding?
- Gemini 3.1 Pro scores higher in coding (60 vs 56 on the category index, where 50 is average).
- Is Claude Opus 4.5 better than Gemini 3.1 Pro for agentic tasks?
- Claude Opus 4.5 scores higher in agentic tasks (75 vs 64 on the category index, where 50 is average).
- Which is cheaper, Claude Opus 4.5 or Gemini 3.1 Pro?
- Gemini 3.1 Pro is cheaper: $4.50 against $10.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Opus 4.5 or Gemini 3.1 Pro?
- Gemini 3.1 Pro streams faster: 108 against 45 output tokens per second.
- Which has the larger context window?
- Gemini 3.1 Pro accepts more context: 1.0M against 200k tokens.