Gemini 3.1 Pro vs GPT-5.5 Pro
Gemini 3.1 Pro 
GPT-5.5 Pro Verdict
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 63.9.
- Gemini 3.1 Pro is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, multimodal.
- GPT-5.5 Pro (xhigh) is stronger in maths, reasoning.
- Gemini 3.1 Pro is 15× cheaper ($4.50 vs $67.50 per 1M blended).
- Gemini 3.1 Pro streams 30.3× faster (121 vs 4 tokens per second).
| Metric | Gemini 3.1 Pro | GPT-5.5 Pro (xhigh) |
|---|---|---|
| BenchLeader Index | 63.9 | 67.1 |
| Agents & tools score | 60.4 | – |
| Coding score | 59.8 | – |
| Composite score | 67.5 | – |
| Human preference score | 59.8 | – |
| Instruction following score | 69.7 | – |
| Knowledge score | 65.9 | – |
| Long context score | 67.5 | – |
| Maths score | 61.9 | 74.5 |
| Multimodal score | 66.0 | – |
| Reasoning score | 70.8 | 80.1 |
| Blended price $/M | $4.50 | $67.50 |
| Output speed | 121 tok/s | 4 tok/s |
| Time to first answer | 34.8 s | 3.5 s |
| Context window | 1.0M | 1.1M |
| GPQA Diamond | 94.1% | – |
| FrontierMath Tiers 1–3 | 59.6% | 87.7% |
| FrontierMath Tier 4 | 26.8% | 78.0% |
| 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 | 1508 | – |
| LMArena Coding | 1520 | – |
| LMArena WebDev | 1447 | – |
| LMArena Vision | 1296 | – |
| LMArena Agent | -5.8 | – |
| AA Intelligence Index | 30.4 | – |
| IFBench | 77.1% | – |
| AA-LCR | 82.0% | – |
| MMMU-Pro | 82.4% | – |
| AA-Omniscience | 31.9 | – |
| Terminal-Bench Hard | 53.8% | – |
| GPQA Diamond (AA) | 94.1% | – |
| Humanity's Last Exam (AA) | 47.0% | – |
| SciCode (AA) | 58.7% | – |
| τ²-Bench Telecom (AA) | 95.6% | – |
| 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% | – |
| TutorBench | 53.0% | – |
| EQ-Bench 4 | 1142 | – |
| ARC-AGI-1 | 98.0% | 95.0% |
| ARC-AGI-2 | 77.1% | 84.2% |
| ARC-AGI-3 | 0.4% | – |
| CritPt | 17.7% | 30.6% |
| GDPval (AA) | 20.2% | – |
| τ²-Bench Banking (AA) | 21.4% | – |
| ITBench SRE (AA) | 30.3% | – |
| Analyst Agent (AA) | 41.3% | – |
| APEX-Agents (AA) | 32.0% | – |
| CyberBench | 36.4% | – |
| FORTRESS | 29.8% | – |
| MASK | 42.4% | – |
| SWE Atlas: Codebase QnA | 13.5% | – |
| SWE Atlas: Refactoring | 33.8% | – |
| SWE Atlas: Test Writing | 29.8% | – |
| VTB | 29.0% | – |
| LMArena Maths | 1489 | – |
| LMArena Creative Writing | 1480 | – |
| LMArena Instruction Following | 1481 | – |
| LMArena Multi-turn | 1495 | – |
| LMArena Longer Queries | 1500 | – |
| LMArena Document | 1459 | – |
| Chess Puzzles | 55.0% | – |
| EBR-bench | 14.3% | – |
| BALROG | 57.0% | – |
| PostTrainBench | 22.0% | – |
| ExploitBench | 26.1% | – |
| CL-bench | 20.8% | – |
| CL-bench Life | 16.9% | – |
| METR Time Horizons | 77.0% | – |
| DeepSWE | 11.7% | – |
| LMCA | – | 53.9% |
| DTBench | – | 96.0% |
| ForecastBench | 59.0% | – |
| GBAEval | 0.8% | – |
| ALE-Bench | 1160.6 | – |
| AlgoTune | 2.0 | – |
| Vending-Bench 2 | 911.2 | – |
| Blueprint-Bench 2 | 26.5% | – |
| GDP.pdf | 17.0% | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Gemini 3.1 Pro vs GPT-5.5 Pro: questions
- Is Gemini 3.1 Pro better than GPT-5.5 Pro?
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 63.9. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 Pro (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, Gemini 3.1 Pro or GPT-5.5 Pro?
- Gemini 3.1 Pro is cheaper: $4.50 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, Gemini 3.1 Pro or GPT-5.5 Pro?
- Gemini 3.1 Pro streams faster: 121 against 4 output tokens per second.
- Which has the larger context window?
- GPT-5.5 Pro accepts more context: 1.1M against 1.0M tokens.