Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-4.1
Gemini 2.0 Flash (Feb 2025) and GPT-4.1 score almost the same on the Noometry Index (34.8 vs 35.7), so choose on price, context window or the category you care about most.
Last verified . 41 shared benchmarks.
GoogleSummary
- They share 41 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 3 categories and GPT-4.1 in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 36.1 to 21.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 39.6% for GPT-4.1.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-4.1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 34.8 | 35.7 |
| Released | 2024-12-06 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 54 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 28.2 (#308), GPT-4.1: 34.2 (#228)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 39.6% |
| Aider Polyglot | 38.2% | 52.4% |
| WeirdML | 25.8% | 39% |
| LMArena Coding | 1351 | 1391 |
| CadEval | 30% | 42% |
| SWE-bench Verified | — | 48.5% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| ALE-Bench | — | 558.1 |
Agentic & Tool Use GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), GPT-4.1: 34.4 (#40)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| TheAgentCompany | 11.4% | — |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), GPT-4.1: 11.7 (#334)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0.4% |
| SimpleBench | 31.1% | 27% |
| Kagi LLM Benchmark | 37.8% | 52.3% |
| EnigmaEval | 1.1% | 2.2% |
| LMArena Hard Prompts | 1346 | 1384 |
| DTBench | 63.2% | 68.3% |
| Epoch Capabilities Index | 135.36 | 136.79 |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 78.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 25.6% |
| ForecastBench | — | 61.5 |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), GPT-4.1: 21.4 (#269)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 38.3% |
| Omni-MATH | 45.9% | 47.1% |
| LMArena Math | 1351 | 1369 |
| MATH Level 5 | 82.2% | 83% |
| FrontierMath (Feb 2025 set) | 1.7% | 5.5% |
| FrontierMath (Tiers 1-3) | — | 6% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), GPT-4.1: 37.0 (#152)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 64.1% | 66.9% |
| Humanity's Last Exam | 6.6% | 5.4% |
| MMLU-Pro | 73.7% | 81.1% |
| GPQA (HELM) | 55.6% | 65.9% |
| LMArena Expert | 1340 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 5.6% |
| MMLU | 79.7% | — |
Multimodal GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), GPT-4.1: 37.5 (#66)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1158 | 1210 |
| GeoBench | 77% | 72% |
Multilingual GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), GPT-4.1: 49.6 (#128)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1342 | 1370 |
| LMArena Chinese | 1373 | 1382 |
| LMArena French | 1390 | 1383 |
| LMArena German | 1354 | 1380 |
| LMArena Japanese | 1293 | 1320 |
| LMArena Korean | 1314 | 1339 |
| LMArena Russian | 1351 | 1377 |
| LMArena Spanish | 1363 | 1375 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), GPT-4.1: 71.5 (#148)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| IFEval | 84.1% | 83.8% |
| LMArena Instruction Following | 1336 | 1367 |
| LiveBench Instruction Following | 85.8% | — |
Long Context GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), GPT-4.1: 40.0 (#158)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 63.9% |
| LMArena Longer Query | 1345 | 1385 |
Writing & Preference GPT-4.1 leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), GPT-4.1: 57.8 (#120)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 |
|---|---|---|
| LMArena Text | 1354 | 1383 |
| LMArena Creative Writing | 1340 | 1363 |
| EQ-Bench Creative Writing | 1128 | 1420 |
| WildBench | 80% | 85.4% |
| LMArena Multi-Turn | 1350 | 1398 |
| Short-Story Creative Writing | 73.8% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-4.1?
Gemini 2.0 Flash (Feb 2025) and GPT-4.1 score almost the same on the Noometry Index (34.8 vs 35.7), so choose on price, context window or the category you care about most.
Is Gemini 2.0 Flash (Feb 2025) or GPT-4.1 better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.2 versus 28.2 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-4.1 share?
41 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-4.1 has 52.