Model comparison
Gemini 1.5 Pro (May 2024) vs o3
o3 is the stronger model overall, scoring 47.5 to 32.1 on the Noometry Index.
Last verified . 35 shared benchmarks.
GoogleSummary
- They share 35 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and o3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 84.4% for o3.
Side by side
| Gemini 1.5 Pro (May 2024) | o3 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 47.5 |
| Released | 2024-02-15 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 45 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), o3: 46.8 (#64)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| WeirdML | 22.2% | 52.4% |
| LMArena Coding | 1294 | 1408 |
| CadEval | 34% | 74% |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| ALE-Bench | — | 933.55 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use o3 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), o3: 34.5 (#44)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| BALROG | 21% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), o3: 32.0 (#78)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 6.5% |
| SimpleBench | 27.1% | 53.1% |
| LMArena Hard Prompts | 1296 | 1402 |
| DTBench | 59% | 84.8% |
| Epoch Capabilities Index | 131.73 | 146.86 |
| ForecastBench | 58.4 | 62.5 |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| LMCA | — | 39.7% |
| BIG-Bench Hard | 89.2% | — |
Math o3 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), o3: 50.2 (#58)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 84.4% |
| Omni-MATH | 36.4% | 71.4% |
| LMArena Math | 1315 | 1426 |
| MATH Level 5 | 70.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), o3: 54.6 (#52)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| GPQA Diamond | 57.2% | 81.8% |
| Humanity's Last Exam | 4.6% | 20.3% |
| MMLU-Pro | 73.7% | 85.9% |
| Confabulations | 13.5% | 14.4% |
| GPQA (HELM) | 53.4% | 75.3% |
| LMArena Expert | 1279 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU | 86.9% | — |
Multimodal o3 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), o3: 41.4 (#36)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| LMArena Vision | 1161 | 1214 |
| Video-MME | 75% | — |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), o3: 51.7 (#105)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| LMArena Non-English | 1312 | 1401 |
| LMArena Chinese | 1331 | 1437 |
| LMArena French | 1302 | 1430 |
| LMArena German | 1286 | 1420 |
| LMArena Japanese | 1292 | 1403 |
| LMArena Korean | 1298 | 1370 |
| LMArena Russian | 1320 | 1406 |
| LMArena Spanish | 1311 | 1395 |
Instruction Following o3 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), o3: 72.8 (#127)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| IFEval | 83.7% | 86.9% |
| LMArena Instruction Following | 1297 | 1368 |
Long Context o3 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), o3: 53.3 (#6)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), o3: 63.5 (#64)
| Benchmark | Gemini 1.5 Pro (May 2024) | o3 |
|---|---|---|
| LMArena Text | 1319 | 1410 |
| LMArena Creative Writing | 1333 | 1359 |
| WildBench | 81.3% | 86.1% |
| LMArena Multi-Turn | 1296 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than o3?
o3 is the stronger model overall, scoring 47.5 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and o3 share?
35 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and o3 has 63.