Model comparison
Gemini 3 Pro vs GPT-5.1
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 49.0 on the Noometry Index.
Last verified . 50 shared benchmarks.
GoogleSummary
- They share 50 benchmarks with published results for both. Gemini 3 Pro scores higher in 7 categories and GPT-5.1 in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Pro leads 64.4 to 50.6.
- The biggest single-benchmark swing is GPQA (HELM): 80.3% for Gemini 3 Pro and 44.2% for GPT-5.1.
Side by side
| Gemini 3 Pro | GPT-5.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.8 | 49.0 |
| Released | 2025-11-18 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 67 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 3 Pro: 51.6 (#39), GPT-5.1: 46.4 (#66)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| SWE-bench Verified | 72.9% | 68% |
| SWE-bench Verified (bash only) | 74.2% | 66% |
| LMArena WebDev | 1440 | 1395 |
| GSO | 18.6% | 13.7% |
| WeirdML | 69.9% | 60.8% |
| LMArena Coding | 1481 | 1454 |
| ALE-Bench | 1,177 | 1,192 |
| SWE-bench Multilingual | 68.7% | — |
| SciCode | — | 43.3% |
| LiveBench Coding | — | 72.5% |
| AlgoTune | 1.83 | — |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 3 Pro: 40.6 (#23), GPT-5.1: 32.7 (#60)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| Terminal-Bench | 69.4% | 47.6% |
| DeepResearch Bench | 46.3% | 42.8% |
| LMArena Search | 1207 | 1199 |
| Vending-Bench 2 | 5,478 | 1,473 |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| BALROG | 58.1% | — |
| METR Time Horizons | 71% | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#31), GPT-5.1: 39.8 (#58)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 31.1% | 17.6% |
| SimpleBench | 76.4% | 53.2% |
| ARC-AGI-1 | 75% | 72.8% |
| CritPt | 6.9% | 4.9% |
| Chess Puzzles | 31% | 32% |
| EnigmaEval | 18.2% | 11.2% |
| LMArena Hard Prompts | 1480 | 1457 |
| Epoch Capabilities Index | 152.92 | 149.64 |
| ForecastBench | 61.2 | 58.1 |
| Kagi LLM Benchmark | 80.1% | — |
| NYT Connections (extended) | 94.4% | — |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | — | 72.1% |
| LMCA | — | 43.9% |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
Gemini 3 Pro: 49.9 (#59), GPT-5.1: 52.2 (#51)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 88.6% |
| Omni-MATH | 55.5% | 46.4% |
| LMArena Math | 1476 | 1447 |
| FrontierMath (Feb 2025 set) | 37.6% | 31% |
| FrontierMath Tier 4 (v1) | 18.8% | 12.5% |
| MathArena Final-Answer Competitions | 67% | — |
| ProofBench | 20% | — |
| LiveBench Math | — | 94.5% |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.4 (#16), GPT-5.1: 50.6 (#71)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 92.6% | 87.6% |
| Humanity's Last Exam | 37.5% | 23.7% |
| MMLU-Pro | 90.3% | 57.9% |
| Vectara Hallucination Rate | 13.6% | 10.9% |
| GPQA (HELM) | 80.3% | 44.2% |
| LMArena Expert | 1475 | 1470 |
| SimpleQA Verified | — | 48% |
Multimodal Gemini 3 Pro leads
Gemini 3 Pro: 57.6 (#2), GPT-5.1: 44.8 (#19)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1305 | 1250 |
| VPCT | 91% | 58.7% |
| LMArena Document | 1434 | 1403 |
| GeoBench | 84% | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#16), GPT-5.1: 53.8 (#56)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1474 | 1431 |
| LMArena Chinese | 1523 | 1495 |
| LMArena French | 1492 | 1450 |
| LMArena German | 1515 | 1438 |
| LMArena Japanese | 1510 | 1453 |
| LMArena Korean | 1448 | 1401 |
| LMArena Russian | 1493 | 1435 |
| LMArena Spanish | 1470 | 1433 |
Instruction Following GPT-5.1 leads
Gemini 3 Pro: 76.3 (#45), GPT-5.1: 83.9 (#1)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| IFEval | 87.7% | 93.5% |
| LMArena Instruction Following | 1458 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
Long Context GPT-5.1 leads
Gemini 3 Pro: 44.0 (#79), GPT-5.1: 47.6 (#14)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| CL-bench | 15.8% | 23.7% |
| LMArena Longer Query | 1471 | 1447 |
| CL-bench Life | — | 17.3% |
Writing & Preference Gemini 3 Pro leads
Gemini 3 Pro: 66.4 (#35), GPT-5.1: 64.5 (#55)
| Benchmark | Gemini 3 Pro | GPT-5.1 |
|---|---|---|
| LMArena Text | 1479 | 1443 |
| LMArena Creative Writing | 1482 | 1427 |
| WildBench | 85.9% | 86.3% |
| LMArena Multi-Turn | 1484 | 1450 |
| EQ-Bench Creative Writing | 1525 | — |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is Gemini 3 Pro better than GPT-5.1?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 49.0 on the Noometry Index.
Is Gemini 3 Pro or GPT-5.1 better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 46.4 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and GPT-5.1 share?
50 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and GPT-5.1 has 63.