Model comparison
Gemini 2.0 Flash (Feb 2025) vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 35.1 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 3 categories and o3-mini in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where o3-mini leads 40.8 to 28.4.
- The biggest single-benchmark swing is CadEval: 30% for Gemini 2.0 Flash (Feb 2025) and 54% for o3-mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | o3-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 36.7 |
| Released | 2024-12-06 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 54 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), o3-mini: 40.8 (#132)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| Aider Polyglot | 38.2% | 60.4% |
| WeirdML | 25.8% | 43.7% |
| LiveBench Coding | 63.4% | 82.7% |
| LMArena Coding | 1350 | 1378 |
| CadEval | 30% | 54% |
| SWE-bench Verified (bash only) | 13.5% | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 45.9% | — |
| BigCodeBench Complete | 59.9% | — |
Agentic & Tool Use o3-mini leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), o3-mini: 29.6 (#84)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| TheAgentCompany | 11.4% | — |
| Cybench | — | 22.5% |
Reasoning o3-mini leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), o3-mini: 16.3 (#305)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 3% |
| SimpleBench | 31.1% | 22.8% |
| LiveBench Reasoning | 78.2% | 89.6% |
| LMArena Hard Prompts | 1346 | 1366 |
| DTBench | 63.2% | 68.8% |
| LiveBench Data Analysis | 69.4% | 70.6% |
| Epoch Capabilities Index | 135.36 | 140.34 |
| LiveBench | 66.9% | 75.9% |
| Kagi LLM Benchmark | 37.8% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| EnigmaEval | 1.1% | — |
| Mystery Game Puzzles | — | 7% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), o3-mini: 28.1 (#244)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 76.9% |
| LiveBench Math | 75.8% | 77.3% |
| LMArena Math | 1352 | 1396 |
| MATH Level 5 | 82.2% | 96.5% |
| FrontierMath (Feb 2025 set) | 1.7% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 45.9% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), o3-mini: 38.3 (#146)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| GPQA Diamond | 64.1% | 77% |
| Confabulations | 12.4% | 17.9% |
| LMArena Expert | 1339 | 1364 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), o3-mini: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), o3-mini: 45.7 (#164)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| LMArena Non-English | 1342 | 1319 |
| LMArena Chinese | 1373 | 1379 |
| LMArena French | 1391 | 1334 |
| LMArena German | 1353 | 1303 |
| LMArena Japanese | 1294 | 1286 |
| LMArena Korean | 1313 | 1314 |
| LMArena Russian | 1351 | 1304 |
| LMArena Spanish | 1363 | 1321 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), o3-mini: 75.1 (#72)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 84.4% |
| LMArena Instruction Following | 1336 | 1337 |
| IFEval | 84.1% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), o3-mini: 33.8 (#256)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| Fiction.LiveBench | 61.1% | 50% |
| LMArena Longer Query | 1344 | 1343 |
Writing & Preference Too close to call
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), o3-mini: 50.3 (#182)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3-mini |
|---|---|---|
| LMArena Text | 1354 | 1337 |
| LMArena Creative Writing | 1340 | 1286 |
| Short-Story Creative Writing | 73.8% | 61.7% |
| LMArena Multi-Turn | 1350 | 1320 |
| LiveBench Language | 51.3% | 50.7% |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and o3-mini share?
38 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and o3-mini has 51.