Model comparison
Gemini 2.0 Flash (Feb 2025) vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 35.1 on the Noometry Index.
Last verified . 42 shared benchmarks.
GoogleSummary
- They share 42 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and o4-mini in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where o4-mini leads 40.9 to 28.4.
- The biggest single-benchmark swing is Aider Polyglot: 38.2% for Gemini 2.0 Flash (Feb 2025) and 72% for o4-mini.
Side by side
| Gemini 2.0 Flash (Feb 2025) | o4-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 41.6 |
| Released | 2024-12-06 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 54 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), o4-mini: 40.9 (#127)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 45% |
| Aider Polyglot | 38.2% | 72% |
| WeirdML | 25.8% | 52.6% |
| LMArena Coding | 1350 | 1368 |
| CadEval | 30% | 62% |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), o4-mini: 32.6 (#61)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| TheAgentCompany | 11.4% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), o4-mini: 24.6 (#162)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| ARC-AGI-2 | 1.3% | 6.1% |
| SimpleBench | 31.1% | 38.7% |
| Kagi LLM Benchmark | 37.8% | 67.6% |
| EnigmaEval | 1.1% | 9.2% |
| LMArena Hard Prompts | 1346 | 1351 |
| DTBench | 63.2% | 77.6% |
| Epoch Capabilities Index | 135.36 | 145.64 |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 26.5% |
| ForecastBench | — | 61.8 |
| LiveBench | 66.9% | — |
Math o4-mini leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), o4-mini: 40.8 (#89)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 81.7% |
| Omni-MATH | 45.9% | 72% |
| LMArena Math | 1352 | 1389 |
| MATH Level 5 | 82.2% | 97.8% |
| FrontierMath (Feb 2025 set) | 1.7% | 24.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), o4-mini: 43.6 (#91)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| GPQA Diamond | 64.1% | 79.6% |
| Humanity's Last Exam | 6.6% | 18.1% |
| MMLU-Pro | 73.7% | 82% |
| Confabulations | 12.4% | 15.8% |
| GPQA (HELM) | 55.6% | 73.5% |
| LMArena Expert | 1339 | 1343 |
| SimpleQA Verified | — | 19.6% |
| Vectara Hallucination Rate | — | 18.6% |
| MMLU | 79.7% | — |
Multimodal o4-mini leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), o4-mini: 40.2 (#49)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| LMArena Vision | 1158 | 1194 |
| GeoBench | 77% | 64% |
| VPCT | — | 57.5% |
Multilingual Too close to call
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), o4-mini: 47.0 (#154)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| LMArena Non-English | 1342 | 1337 |
| LMArena Chinese | 1373 | 1354 |
| LMArena French | 1391 | 1364 |
| LMArena German | 1353 | 1336 |
| LMArena Japanese | 1294 | 1308 |
| LMArena Korean | 1313 | 1312 |
| LMArena Russian | 1351 | 1334 |
| LMArena Spanish | 1363 | 1347 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), o4-mini: 75.2 (#68)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| IFEval | 84.1% | 92.8% |
| LMArena Instruction Following | 1336 | 1321 |
| LiveBench Instruction Following | 85.8% | — |
Long Context o4-mini leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), o4-mini: 45.5 (#33)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| Fiction.LiveBench | 61.1% | 77.8% |
| LMArena Longer Query | 1344 | 1315 |
Writing & Preference o4-mini leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), o4-mini: 54.0 (#152)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | o4-mini |
|---|---|---|
| LMArena Text | 1354 | 1353 |
| LMArena Creative Writing | 1340 | 1294 |
| Short-Story Creative Writing | 73.8% | 75% |
| WildBench | 80% | 85.4% |
| LMArena Multi-Turn | 1350 | 1350 |
| EQ-Bench Creative Writing | 1128 | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and o4-mini share?
42 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and o4-mini has 60.