Model comparison
Gemini 2.0 Flash (Feb 2025) vs o3
o3 is the stronger model overall, scoring 47.5 to 35.1 on the Noometry Index.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and o3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 32.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 58.4% for o3.
Side by side
| Gemini 2.0 Flash (Feb 2025) | o3 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 47.5 |
| Released | 2024-12-06 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 54 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), o3: 46.8 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 58.4% |
| Aider Polyglot | 38.2% | 81.3% |
| WeirdML | 25.8% | 52.4% |
| LMArena Coding | 1350 | 1408 |
| CadEval | 30% | 74% |
| SWE-bench Verified | — | 62.3% |
| GSO | — | 8.8% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use o3 leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), o3: 34.5 (#44)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| TheAgentCompany | 11.4% | — |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), o3: 32.0 (#78)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 6.5% |
| SimpleBench | 31.1% | 53.1% |
| Kagi LLM Benchmark | 37.8% | 67.6% |
| EnigmaEval | 1.1% | 13.1% |
| LMArena Hard Prompts | 1346 | 1402 |
| DTBench | 63.2% | 84.8% |
| Epoch Capabilities Index | 135.36 | 146.86 |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 29% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
| LiveBench | 66.9% | — |
Math o3 leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), o3: 50.2 (#58)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 84.4% |
| Omni-MATH | 45.9% | 71.4% |
| LMArena Math | 1352 | 1426 |
| MATH Level 5 | 82.2% | 97.8% |
| FrontierMath (Feb 2025 set) | 1.7% | 18.7% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), o3: 54.6 (#52)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| GPQA Diamond | 64.1% | 81.8% |
| Humanity's Last Exam | 6.6% | 20.3% |
| MMLU-Pro | 73.7% | 85.9% |
| Confabulations | 12.4% | 14.4% |
| GPQA (HELM) | 55.6% | 75.3% |
| LMArena Expert | 1339 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU | 79.7% | — |
Multimodal o3 leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), o3: 41.4 (#36)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| LMArena Vision | 1158 | 1214 |
| GeoBench | 77% | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), o3: 51.7 (#105)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| LMArena Non-English | 1342 | 1401 |
| LMArena Chinese | 1373 | 1437 |
| LMArena French | 1391 | 1430 |
| LMArena German | 1353 | 1420 |
| LMArena Japanese | 1294 | 1403 |
| LMArena Korean | 1313 | 1370 |
| LMArena Russian | 1351 | 1406 |
| LMArena Spanish | 1363 | 1395 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), o3: 72.8 (#127)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| IFEval | 84.1% | 86.9% |
| LMArena Instruction Following | 1336 | 1368 |
| LiveBench Instruction Following | 85.8% | — |
Long Context o3 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), o3: 53.3 (#6)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 88.9% |
| LMArena Longer Query | 1344 | 1372 |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), o3: 63.5 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o3 |
|---|---|---|
| LMArena Text | 1354 | 1410 |
| LMArena Creative Writing | 1340 | 1359 |
| Short-Story Creative Writing | 73.8% | 83.9% |
| EQ-Bench Creative Writing | 1128 | 1676 |
| WildBench | 80% | 86.1% |
| LMArena Multi-Turn | 1350 | 1405 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than o3?
o3 is the stronger model overall, scoring 47.5 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and o3 share?
43 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and o3 has 63.