Model comparison
Gemini 3 Pro vs GPT-4.1
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 35.9 on the Noometry Index.
Last verified . 44 shared benchmarks.
GoogleSummary
- They share 44 benchmarks with published results for both. Gemini 3 Pro scores higher in 10 categories and GPT-4.1 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 75% for Gemini 3 Pro and 5.5% for GPT-4.1.
Side by side
| Gemini 3 Pro | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.8 | 35.9 |
| Released | 2025-11-18 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 67 | 52 |
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-4.1: 34.4 (#238)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 72.9% | 48.5% |
| SWE-bench Verified (bash only) | 74.2% | 39.6% |
| WeirdML | 69.9% | 39% |
| LMArena Coding | 1481 | 1391 |
| ALE-Bench | 1,177 | 558.1 |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1440 | — |
| SWE-bench Multilingual | 68.7% | — |
| GSO | 18.6% | — |
| CadEval | — | 42% |
| AlgoTune | 1.83 | — |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 3 Pro: 40.6 (#23), GPT-4.1: 34.7 (#43)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.5% | 54% |
| Terminal-Bench | 69.4% | — |
| 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% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#31), GPT-4.1: 11.7 (#339)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 31.1% | 0.4% |
| SimpleBench | 76.4% | 27% |
| Kagi LLM Benchmark | 80.1% | 52.3% |
| ARC-AGI-1 | 75% | 5.5% |
| Chess Puzzles | 31% | 6% |
| EnigmaEval | 18.2% | 2.2% |
| LMArena Hard Prompts | 1480 | 1384 |
| Epoch Capabilities Index | 152.92 | 136.78 |
| ForecastBench | 61.2 | 61.5 |
| NYT Connections (extended) | 94.4% | — |
| CritPt | 6.9% | — |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
Math Gemini 3 Pro leads
Gemini 3 Pro: 49.9 (#59), GPT-4.1: 22.3 (#280)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.4% | 38.3% |
| Omni-MATH | 55.5% | 47.1% |
| LMArena Math | 1476 | 1370 |
| FrontierMath (Feb 2025 set) | 37.6% | 5.5% |
| FrontierMath Tier 4 (v1) | 18.8% | 0% |
| FrontierMath (Tiers 1-3) | — | 6% |
| MathArena Final-Answer Competitions | 67% | — |
| ProofBench | 20% | — |
| MATH Level 5 | — | 83% |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.4 (#16), GPT-4.1: 37.1 (#160)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 92.6% | 66.9% |
| Humanity's Last Exam | 37.5% | 5.4% |
| MMLU-Pro | 90.3% | 81.1% |
| Vectara Hallucination Rate | 13.6% | 5.6% |
| GPQA (HELM) | 80.3% | 65.9% |
| LMArena Expert | 1475 | 1364 |
| SimpleQA Verified | — | 31.1% |
Multimodal Gemini 3 Pro leads
Gemini 3 Pro: 57.6 (#2), GPT-4.1: 38.2 (#67)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1305 | 1211 |
| GeoBench | 84% | 72% |
| VPCT | 91% | — |
| LMArena Document | 1434 | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#16), GPT-4.1: 49.4 (#133)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1474 | 1370 |
| LMArena Chinese | 1523 | 1382 |
| LMArena French | 1492 | 1382 |
| LMArena German | 1515 | 1381 |
| LMArena Japanese | 1510 | 1319 |
| LMArena Korean | 1448 | 1339 |
| LMArena Russian | 1493 | 1377 |
| LMArena Spanish | 1470 | 1376 |
Instruction Following Gemini 3 Pro leads
Gemini 3 Pro: 76.3 (#45), GPT-4.1: 71.3 (#153)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| IFEval | 87.7% | 83.8% |
| LMArena Instruction Following | 1458 | 1367 |
Long Context Gemini 3 Pro leads
Gemini 3 Pro: 44.0 (#79), GPT-4.1: 40.0 (#163)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1471 | 1385 |
| Fiction.LiveBench | — | 63.9% |
| CL-bench | 15.8% | — |
Writing & Preference Gemini 3 Pro leads
Gemini 3 Pro: 66.4 (#35), GPT-4.1: 57.6 (#125)
| Benchmark | Gemini 3 Pro | GPT-4.1 |
|---|---|---|
| LMArena Text | 1479 | 1383 |
| LMArena Creative Writing | 1482 | 1363 |
| EQ-Bench Creative Writing | 1525 | 1420 |
| WildBench | 85.9% | 85.4% |
| LMArena Multi-Turn | 1484 | 1398 |
Frequently asked questions
Is Gemini 3 Pro better than GPT-4.1?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 35.9 on the Noometry Index.
Is Gemini 3 Pro or GPT-4.1 better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and GPT-4.1 share?
44 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and GPT-4.1 has 52.