Model comparison
Gemini 1.5 Pro (May 2024) vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 32.1 on the Noometry Index.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 2 categories and o3-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3-mini leads 29.6 to 17.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 76.9% for o3-mini.
Side by side
| Gemini 1.5 Pro (May 2024) | o3-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 36.7 |
| Released | 2024-02-15 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 45 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), o3-mini: 40.8 (#132)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| WeirdML | 22.2% | 43.7% |
| LMArena Coding | 1294 | 1378 |
| CadEval | 34% | 54% |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 43.8% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 57.5% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use o3-mini leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), o3-mini: 29.6 (#84)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| Cybench | 7.5% | 22.5% |
| TheAgentCompany | 3.4% | — |
| BALROG | 21% | — |
Reasoning o3-mini leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), o3-mini: 16.3 (#305)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 3% |
| SimpleBench | 27.1% | 22.8% |
| LMArena Hard Prompts | 1296 | 1366 |
| DTBench | 59% | 68.8% |
| Epoch Capabilities Index | 131.73 | 140.34 |
| ForecastBench | 58.4 | 59.6 |
| 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% |
| BIG-Bench Hard | 89.2% | — |
| LiveBench | — | 75.9% |
Math o3-mini leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), o3-mini: 28.1 (#244)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 76.9% |
| LMArena Math | 1315 | 1396 |
| MATH Level 5 | 70.4% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), o3-mini: 38.3 (#146)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| GPQA Diamond | 57.2% | 77% |
| Confabulations | 13.5% | 17.9% |
| LMArena Expert | 1279 | 1364 |
| Humanity's Last Exam | 4.6% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), o3-mini: —
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Too close to call
Gemini 1.5 Pro (May 2024): 45.3 (#174), o3-mini: 45.7 (#164)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| LMArena Non-English | 1312 | 1319 |
| LMArena Chinese | 1331 | 1379 |
| LMArena French | 1302 | 1334 |
| LMArena German | 1286 | 1303 |
| LMArena Japanese | 1292 | 1286 |
| LMArena Korean | 1298 | 1314 |
| LMArena Russian | 1320 | 1304 |
| LMArena Spanish | 1311 | 1321 |
Instruction Following o3-mini leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), o3-mini: 75.1 (#72)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1297 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), o3-mini: 33.8 (#256)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), o3-mini: 50.3 (#182)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3-mini |
|---|---|---|
| LMArena Text | 1319 | 1337 |
| LMArena Creative Writing | 1333 | 1286 |
| LMArena Multi-Turn | 1296 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| WildBench | 81.3% | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and o3-mini share?
29 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and o3-mini has 51.