Model comparison
Gemini 2.5 Pro vs GPT-4.1
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 35.9 on the Noometry Index.
Last verified . 50 shared benchmarks.
GoogleSummary
- They share 50 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 9 categories and GPT-4.1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 40.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro and 38.3% for GPT-4.1.
- Both cost about the same: $1.25 input and $10 output per million tokens.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1.05M.
Side by side
| Gemini 2.5 Pro | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 45.0 | 35.9 |
| Released | 2025-03-25 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 33K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $8 |
| Results tracked | 78 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Gemini 2.5 Pro: 42.4 (#101), GPT-4.1: 34.4 (#238)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 57.6% | 48.5% |
| SWE-bench Verified (bash only) | 53.6% | 39.6% |
| Aider Polyglot | 83.1% | 52.4% |
| WeirdML | 54% | 39% |
| LMArena Coding | 1452 | 1391 |
| CadEval | 64% | 42% |
| ALE-Bench | 785.52 | 558.1 |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use GPT-4.1 leads
Gemini 2.5 Pro: 29.2 (#88), GPT-4.1: 34.7 (#43)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#99), GPT-4.1: 11.7 (#339)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0.4% |
| SimpleBench | 62.4% | 27% |
| Kagi LLM Benchmark | 70.3% | 52.3% |
| ARC-AGI-1 | 41% | 5.5% |
| Chess Puzzles | 20% | 6% |
| EnigmaEval | 5.6% | 2.2% |
| LMArena Hard Prompts | 1455 | 1384 |
| DTBench | 82.4% | 68.3% |
| LMCA | 34.8% | 25.6% |
| Epoch Capabilities Index | 145.32 | 136.78 |
| ForecastBench | 61.3 | 61.5 |
| CritPt | 2% | — |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| LiveBench | 82.3% | — |
Math Gemini 2.5 Pro leads
Gemini 2.5 Pro: 32.5 (#213), GPT-4.1: 22.3 (#280)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 6% |
| OTIS Mock AIME 2024-2025 | 84.7% | 38.3% |
| Omni-MATH | 41.6% | 47.1% |
| LMArena Math | 1450 | 1370 |
| MATH Level 5 | 95.9% | 83% |
| FrontierMath (Feb 2025 set) | 14.1% | 5.5% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath Tier 4 | 0% | — |
| LiveBench Math | 90.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), GPT-4.1: 37.1 (#160)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 85.3% | 66.9% |
| Humanity's Last Exam | 21.6% | 5.4% |
| MMLU-Pro | 86.3% | 81.1% |
| Vectara Hallucination Rate | 7% | 5.6% |
| GPQA (HELM) | 74.9% | 65.9% |
| LMArena Expert | 1452 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 10.6% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), GPT-4.1: 38.2 (#67)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1263 | 1211 |
| GeoBench | 86% | 72% |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), GPT-4.1: 49.4 (#133)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1451 | 1370 |
| LMArena Chinese | 1507 | 1382 |
| LMArena French | 1472 | 1382 |
| LMArena German | 1487 | 1381 |
| LMArena Japanese | 1461 | 1319 |
| LMArena Korean | 1434 | 1339 |
| LMArena Russian | 1461 | 1377 |
| LMArena Spanish | 1473 | 1376 |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.0 (#75), GPT-4.1: 71.3 (#153)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| IFEval | 84% | 83.8% |
| LMArena Instruction Following | 1437 | 1367 |
| LiveBench Instruction Following | 80.6% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), GPT-4.1: 40.0 (#163)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | 91.7% | 63.9% |
| LMArena Longer Query | 1449 | 1385 |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.7 (#62), GPT-4.1: 57.6 (#125)
| Benchmark | Gemini 2.5 Pro | GPT-4.1 |
|---|---|---|
| LMArena Text | 1458 | 1383 |
| LMArena Creative Writing | 1454 | 1363 |
| EQ-Bench Creative Writing | 1421 | 1420 |
| WildBench | 85.7% | 85.4% |
| LMArena Multi-Turn | 1453 | 1398 |
| Short-Story Creative Writing | 83.8% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than GPT-4.1?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 35.9 on the Noometry Index.
Which is cheaper, Gemini 2.5 Pro or GPT-4.1?
Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-4.1 lists at $2 and $8.
Is Gemini 2.5 Pro or GPT-4.1 better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 1.05M.
How many benchmarks do Gemini 2.5 Pro and GPT-4.1 share?
50 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-4.1 has 52.