Model comparison
Gemini 1.5 Flash (May 2024) vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 33.2 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 2 categories and o3-mini in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 26.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.3% for Gemini 1.5 Flash (May 2024) and 76.9% for o3-mini.
Side by side
| Gemini 1.5 Flash (May 2024) | o3-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 33.2 | 36.7 |
| Released | 2024-05-14 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 42 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Gemini 1.5 Flash (May 2024): 34.4 (#236), o3-mini: 40.8 (#132)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| WeirdML | 24.9% | 43.7% |
| LMArena Coding | 1261 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 43.5% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 55.1% | — |
| CadEval | — | 54% |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use o3-mini leads
Gemini 1.5 Flash (May 2024): 26.6 (#102), o3-mini: 29.6 (#84)
Reasoning Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 21.7 (#215), o3-mini: 16.3 (#305)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1366 |
| DTBench | 53.8% | 68.8% |
| Epoch Capabilities Index | 129.36 | 140.34 |
| ForecastBench | 53.9 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| LiveBench | — | 75.9% |
| PIQA | 87.5% | — |
Math o3-mini leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), o3-mini: 28.1 (#244)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 76.9% |
| LMArena Math | 1269 | 1396 |
| MATH Level 5 | 61.9% | 96.5% |
| FrontierMath (Feb 2025 set) | 0% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 30.4% | — |
| LiveBench Math | — | 77.3% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 82.4% | — |
Knowledge o3-mini leads
Gemini 1.5 Flash (May 2024): 26.2 (#260), o3-mini: 38.3 (#146)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| GPQA Diamond | 47.3% | 77% |
| LMArena Expert | 1233 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 67.8% | — |
| Confabulations | — | 17.9% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 36.0 (#81), o3-mini: —
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual o3-mini leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), o3-mini: 45.7 (#164)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Non-English | 1278 | 1319 |
| LMArena Chinese | 1295 | 1379 |
| LMArena French | 1258 | 1334 |
| LMArena German | 1262 | 1303 |
| LMArena Japanese | 1252 | 1286 |
| LMArena Korean | 1221 | 1314 |
| LMArena Russian | 1288 | 1304 |
| LMArena Spanish | 1243 | 1321 |
Instruction Following o3-mini leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), o3-mini: 75.1 (#72)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1258 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 83.1% | — |
Long Context Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 39.0 (#187), o3-mini: 33.8 (#256)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Longer Query | 1284 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), o3-mini: 50.3 (#182)
| Benchmark | Gemini 1.5 Flash (May 2024) | o3-mini |
|---|---|---|
| LMArena Text | 1287 | 1337 |
| LMArena Creative Writing | 1285 | 1286 |
| LMArena Multi-Turn | 1253 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| WildBench | 79.2% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 33.2 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and o3-mini share?
25 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and o3-mini has 51.