Model comparison
Gemini 1.5 Pro (May 2024) vs GPT-4.1
GPT-4.1 is the stronger model overall, scoring 35.9 to 32.1 on the Noometry Index.
Last verified . 34 shared benchmarks.
GoogleSummary
- They share 34 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 2 categories and GPT-4.1 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-4.1 leads 34.7 to 17.9.
- The biggest single-benchmark swing is WeirdML: 22.2% for Gemini 1.5 Pro (May 2024) and 39% for GPT-4.1.
Side by side
| Gemini 1.5 Pro (May 2024) | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 35.9 |
| Released | 2024-02-15 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 45 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Pro (May 2024): 34.2 (#241), GPT-4.1: 34.4 (#238)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| WeirdML | 22.2% | 39% |
| LMArena Coding | 1294 | 1391 |
| CadEval | 34% | 42% |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| ALE-Bench | — | 558.1 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), GPT-4.1: 34.7 (#43)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Too close to call
Gemini 1.5 Pro (May 2024): 12.3 (#338), GPT-4.1: 11.7 (#339)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0.4% |
| SimpleBench | 27.1% | 27% |
| LMArena Hard Prompts | 1296 | 1384 |
| DTBench | 59% | 68.3% |
| Epoch Capabilities Index | 131.73 | 136.78 |
| ForecastBench | 58.4 | 61.5 |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| LMCA | — | 25.6% |
| BIG-Bench Hard | 89.2% | — |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), GPT-4.1: 22.3 (#280)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 38.3% |
| Omni-MATH | 36.4% | 47.1% |
| LMArena Math | 1315 | 1370 |
| MATH Level 5 | 70.4% | 83% |
| FrontierMath (Tiers 1-3) | — | 6% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), GPT-4.1: 37.1 (#160)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 57.2% | 66.9% |
| Humanity's Last Exam | 4.6% | 5.4% |
| MMLU-Pro | 73.7% | 81.1% |
| GPQA (HELM) | 53.4% | 65.9% |
| LMArena Expert | 1279 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 5.6% |
| MMLU | 86.9% | — |
Multimodal GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), GPT-4.1: 38.2 (#67)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1161 | 1211 |
| Video-MME | 75% | — |
| GeoBench | — | 72% |
Multilingual GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), GPT-4.1: 49.4 (#133)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1312 | 1370 |
| LMArena Chinese | 1331 | 1382 |
| LMArena French | 1302 | 1382 |
| LMArena German | 1286 | 1381 |
| LMArena Japanese | 1292 | 1319 |
| LMArena Korean | 1298 | 1339 |
| LMArena Russian | 1320 | 1377 |
| LMArena Spanish | 1311 | 1376 |
Instruction Following GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), GPT-4.1: 71.3 (#153)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| IFEval | 83.7% | 83.8% |
| LMArena Instruction Following | 1297 | 1367 |
Long Context Too close to call
Gemini 1.5 Pro (May 2024): 39.8 (#169), GPT-4.1: 40.0 (#163)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1308 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.1 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), GPT-4.1: 57.6 (#125)
| Benchmark | Gemini 1.5 Pro (May 2024) | GPT-4.1 |
|---|---|---|
| LMArena Text | 1319 | 1383 |
| LMArena Creative Writing | 1333 | 1363 |
| WildBench | 81.3% | 85.4% |
| LMArena Multi-Turn | 1296 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than GPT-4.1?
GPT-4.1 is the stronger model overall, scoring 35.9 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or GPT-4.1 better for coding?
They score almost the same on coding (34.2 vs 34.4); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Pro (May 2024) and GPT-4.1 share?
34 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and GPT-4.1 has 52.