Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-4.1 mini
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 33.6 on the Noometry Index.
Last verified . 38 shared benchmarks.
GoogleSummary
- They share 38 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 7 categories and GPT-4.1 mini in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 24.1.
- The biggest single-benchmark swing is Fiction.LiveBench: 61.1% for Gemini 2.0 Flash (Feb 2025) and 44.4% for GPT-4.1 mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 33.6 |
| Released | 2024-12-06 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 54 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 mini leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-4.1 mini: 30.6 (#293)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 23.9% |
| Aider Polyglot | 38.2% | 32.4% |
| WeirdML | 25.8% | 37.6% |
| BigCodeBench Instruct | 45.9% | 48.9% |
| LMArena Coding | 1350 | 1367 |
| CadEval | 30% | 16% |
| SciCode | — | 40.4% |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
Agentic & Tool Use GPT-4.1 mini leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-4.1 mini: 33.3 (#55)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |
| TheAgentCompany | 11.4% | — |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-4.1 mini: 10.8 (#340)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0% |
| Kagi LLM Benchmark | 37.8% | 48.6% |
| LMArena Hard Prompts | 1346 | 1349 |
| DTBench | 63.2% | 68.8% |
| Epoch Capabilities Index | 135.36 | 135.01 |
| SimpleBench | 31.1% | — |
| ARC-AGI-1 | — | 3.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 21.1% |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-4.1 mini: 24.1 (#270)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 44.7% |
| Omni-MATH | 45.9% | 49.1% |
| LMArena Math | 1352 | 1343 |
| MATH Level 5 | 82.2% | 87.3% |
| FrontierMath (Feb 2025 set) | 1.7% | 4.5% |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| LiveBench Math | 75.8% | — |
Knowledge GPT-4.1 mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-4.1 mini: 34.7 (#194)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 64.1% | 65.8% |
| MMLU-Pro | 73.7% | 78.3% |
| GPQA (HELM) | 55.6% | 61.4% |
| LMArena Expert | 1339 | 1338 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 12.7% |
| Confabulations | 12.4% | — |
| MMLU | 79.7% | — |
Multimodal Too close to call
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-4.1 mini: 35.8 (#82)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 1158 | 1181 |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-4.1 mini: 45.7 (#166)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1342 | 1318 |
| LMArena Chinese | 1373 | 1329 |
| LMArena French | 1391 | 1358 |
| LMArena German | 1353 | 1351 |
| LMArena Japanese | 1294 | 1290 |
| LMArena Korean | 1313 | 1298 |
| LMArena Russian | 1351 | 1324 |
| LMArena Spanish | 1363 | 1319 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-4.1 mini: 73.7 (#118)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| IFEval | 84.1% | 90.4% |
| LMArena Instruction Following | 1336 | 1333 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-4.1 mini: 31.8 (#275)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| Fiction.LiveBench | 61.1% | 44.4% |
| LMArena Longer Query | 1344 | 1344 |
Writing & Preference Too close to call
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-4.1 mini: 48.6 (#199)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1354 | 1340 |
| LMArena Creative Writing | 1340 | 1300 |
| EQ-Bench Creative Writing | 1128 | 1147 |
| WildBench | 80% | 83.8% |
| LMArena Multi-Turn | 1350 | 1354 |
| 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 mini?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 33.6 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-4.1 mini better for coding?
GPT-4.1 mini scores higher on coding benchmarks: 30.6 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-4.1 mini share?
38 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-4.1 mini has 47.