Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-4o mini
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 25.5 on the Noometry Index.
Last verified . 47 shared benchmarks.
GoogleSummary
- They share 47 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 9 categories and GPT-4o mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 6.9% for GPT-4o mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-4o mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 25.5 |
| Released | 2024-12-06 | 2024-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 54 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-4o mini: 22.0 (#335)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 38.2% | 3.6% |
| WeirdML | 25.8% | 11.8% |
| BigCodeBench Instruct | 45.9% | 46.1% |
| LiveBench Coding | 63.4% | 43.1% |
| LMArena Coding | 1350 | 1290 |
| BigCodeBench Complete | 59.9% | 57.4% |
| SWE-bench Verified (bash only) | 13.5% | — |
| CadEval | 30% | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Too close to call
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-4o mini: 27.5 (#101)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| TheAgentCompany | 11.4% | — |
| BALROG | — | 17.4% |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-4o mini: 8.7 (#347)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0% |
| SimpleBench | 31.1% | 10.7% |
| Kagi LLM Benchmark | 37.8% | 28.8% |
| LiveBench Reasoning | 78.2% | 32.8% |
| LMArena Hard Prompts | 1346 | 1267 |
| DTBench | 63.2% | 54.4% |
| LiveBench Data Analysis | 69.4% | 50% |
| Epoch Capabilities Index | 135.36 | 126.56 |
| LiveBench | 66.9% | 41.3% |
| Chess Puzzles | — | 0% |
| EnigmaEval | 1.1% | — |
| Mystery Game Puzzles | — | 12% |
| LMCA | — | 10.4% |
| PIQA | — | 88.7% |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-4o mini: 10.4 (#314)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 6.9% |
| Omni-MATH | 45.9% | 28% |
| LiveBench Math | 75.8% | 36.3% |
| LMArena Math | 1352 | 1267 |
| MATH Level 5 | 82.2% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| FrontierMath (Feb 2025 set) | 1.7% | — |
| GSM8K | — | 91.3% |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-4o mini: 17.7 (#284)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 64.1% | 37.7% |
| MMLU-Pro | 73.7% | 60.3% |
| Confabulations | 12.4% | 37.2% |
| GPQA (HELM) | 55.6% | 36.8% |
| LMArena Expert | 1339 | 1235 |
| MMLU | 79.7% | 81.8% |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 8.3% |
| BoolQ | — | 88.7% |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-4o mini: 25.9 (#122)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1158 | 1066 |
| GeoBench | 77% | 64% |
| Video-MME | — | 64.8% |
| VPCT | — | 34% |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-4o mini: 42.0 (#199)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1342 | 1266 |
| LMArena Chinese | 1373 | 1265 |
| LMArena French | 1391 | 1297 |
| LMArena German | 1353 | 1272 |
| LMArena Japanese | 1294 | 1216 |
| LMArena Korean | 1313 | 1195 |
| LMArena Russian | 1351 | 1275 |
| LMArena Spanish | 1363 | 1276 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-4o mini: 61.9 (#239)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 56.8% |
| IFEval | 84.1% | 78.2% |
| LMArena Instruction Following | 1336 | 1258 |
Long Context GPT-4o mini leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-4o mini: 39.1 (#186)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1344 | 1289 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-4o mini: 39.5 (#248)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o mini |
|---|---|---|
| LMArena Text | 1354 | 1286 |
| LMArena Creative Writing | 1340 | 1268 |
| Short-Story Creative Writing | 73.8% | 67.2% |
| EQ-Bench Creative Writing | 1128 | 873 |
| WildBench | 80% | 79.1% |
| LMArena Multi-Turn | 1350 | 1285 |
| LiveBench Language | 51.3% | 28.6% |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-4o mini?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 25.5 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-4o mini better for coding?
Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.4 versus 22.0 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-4o mini share?
47 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-4o mini has 60.