Model comparison
Gemini 1.5 Pro (May 2024) vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 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 o4-mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.8 to 25.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 81.7% for o4-mini.
Side by side
| Gemini 1.5 Pro (May 2024) | o4-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 32.1 | 41.6 |
| Released | 2024-02-15 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 45 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), o4-mini: 40.9 (#127)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| WeirdML | 22.2% | 52.6% |
| LMArena Coding | 1294 | 1368 |
| CadEval | 34% | 62% |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use o4-mini leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), o4-mini: 32.6 (#61)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), o4-mini: 24.6 (#162)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 6.1% |
| SimpleBench | 27.1% | 38.7% |
| LMArena Hard Prompts | 1296 | 1351 |
| DTBench | 59% | 77.6% |
| Epoch Capabilities Index | 131.73 | 145.64 |
| ForecastBench | 58.4 | 61.8 |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| LMCA | — | 26.5% |
| BIG-Bench Hard | 89.2% | — |
Math o4-mini leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), o4-mini: 40.8 (#89)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 81.7% |
| Omni-MATH | 36.4% | 72% |
| LMArena Math | 1315 | 1389 |
| MATH Level 5 | 70.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), o4-mini: 43.6 (#91)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| GPQA Diamond | 57.2% | 79.6% |
| Humanity's Last Exam | 4.6% | 18.1% |
| MMLU-Pro | 73.7% | 82% |
| Confabulations | 13.5% | 15.8% |
| GPQA (HELM) | 53.4% | 73.5% |
| LMArena Expert | 1279 | 1343 |
| SimpleQA Verified | — | 19.6% |
| Vectara Hallucination Rate | — | 18.6% |
| MMLU | 86.9% | — |
Multimodal o4-mini leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), o4-mini: 40.2 (#49)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| LMArena Vision | 1161 | 1194 |
| Video-MME | 75% | — |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), o4-mini: 47.0 (#154)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| LMArena Non-English | 1312 | 1337 |
| LMArena Chinese | 1331 | 1354 |
| LMArena French | 1302 | 1364 |
| LMArena German | 1286 | 1336 |
| LMArena Japanese | 1292 | 1308 |
| LMArena Korean | 1298 | 1312 |
| LMArena Russian | 1320 | 1334 |
| LMArena Spanish | 1311 | 1347 |
Instruction Following o4-mini leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), o4-mini: 75.2 (#68)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| IFEval | 83.7% | 92.8% |
| LMArena Instruction Following | 1297 | 1321 |
Long Context o4-mini leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), o4-mini: 45.5 (#33)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| LMArena Longer Query | 1308 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), o4-mini: 54.0 (#152)
| Benchmark | Gemini 1.5 Pro (May 2024) | o4-mini |
|---|---|---|
| LMArena Text | 1319 | 1353 |
| LMArena Creative Writing | 1333 | 1294 |
| WildBench | 81.3% | 85.4% |
| LMArena Multi-Turn | 1296 | 1350 |
| Short-Story Creative Writing | — | 75% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and o4-mini share?
35 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and o4-mini has 60.