Model comparison
Gemini 2.5 Flash vs o3-mini
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.7 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 7 categories and o3-mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Flash leads 47.5 to 33.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 77.8% for Gemini 2.5 Flash and 50% for o3-mini.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 2.5 Flash | o3-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.3 | 36.7 |
| Released | 2025-04-17 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.30 | $1.10 |
| Output $ / M tokens | $2.50 | $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 2.5 Flash: 35.8 (#220), o3-mini: 40.8 (#132)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| Aider Polyglot | 55.1% | 60.4% |
| WeirdML | 41.9% | 43.7% |
| LMArena Coding | 1424 | 1378 |
| SWE-bench Verified (bash only) | 28.7% | — |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.8 (#74), o3-mini: 29.6 (#84)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| Cybench | — | 22.5% |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.1 (#286), o3-mini: 16.3 (#305)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| ARC-AGI-2 | 2.5% | 3% |
| SimpleBench | 41.2% | 22.8% |
| ARC-AGI-1 | 33.3% | 34.5% |
| CritPt | 1.1% | 0.3% |
| LMArena Hard Prompts | 1422 | 1366 |
| DTBench | 76.5% | 68.8% |
| LMCA | 27.5% | 19% |
| Epoch Capabilities Index | 143.03 | 140.34 |
| ForecastBench | 60.6 | 59.6 |
| Kagi LLM Benchmark | 56.8% | — |
| Chess Puzzles | — | 17% |
| EnigmaEval | 2.7% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), o3-mini: 28.1 (#244)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 76.9% |
| LMArena Math | 1415 | 1396 |
| FrontierMath (Feb 2025 set) | 4.8% | 12.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 38.5% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
Knowledge o3-mini leads
Gemini 2.5 Flash: 36.4 (#168), o3-mini: 38.3 (#146)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| Confabulations | 16.8% | 17.9% |
| LMArena Expert | 1426 | 1364 |
| GPQA Diamond | — | 77% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 63.9% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), o3-mini: —
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), o3-mini: 45.7 (#164)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| LMArena Non-English | 1409 | 1319 |
| LMArena Chinese | 1450 | 1379 |
| LMArena French | 1433 | 1334 |
| LMArena German | 1418 | 1303 |
| LMArena Japanese | 1405 | 1286 |
| LMArena Korean | 1385 | 1314 |
| LMArena Russian | 1415 | 1304 |
| LMArena Spanish | 1421 | 1321 |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.7 (#54), o3-mini: 75.1 (#72)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1405 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), o3-mini: 33.8 (#256)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| Fiction.LiveBench | 77.8% | 50% |
| LMArena Longer Query | 1419 | 1343 |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 53.8 (#157), o3-mini: 50.3 (#182)
| Benchmark | Gemini 2.5 Flash | o3-mini |
|---|---|---|
| LMArena Text | 1417 | 1337 |
| LMArena Creative Writing | 1400 | 1286 |
| Short-Story Creative Writing | 76.5% | 61.7% |
| LMArena Multi-Turn | 1408 | 1320 |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Gemini 2.5 Flash better than o3-mini?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.7 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or o3-mini?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Gemini 2.5 Flash or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 2.5 Flash and o3-mini share?
33 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and o3-mini has 51.