Model comparison
Gemini 2.5 Pro vs o1
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 40.9 on the Noometry Index.
Last verified . 48 shared benchmarks.
GoogleSummary
- They share 48 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 8 categories and o1 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 41.5.
- The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 61.7% for o1.
- Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $15 / $60 for o1.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 2.5 Pro | o1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 45.0 | 40.9 |
| Released | 2025-03-25 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $1.25 | $15 |
| Output $ / M tokens | $10 | $60 |
| Results tracked | 78 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Gemini 2.5 Pro: 42.4 (#101), o1: 46.1 (#70)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| Aider Polyglot | 83.1% | 61.7% |
| WeirdML | 54% | 47.6% |
| LiveBench Coding | 85.9% | 69.7% |
| LMArena Coding | 1452 | 1367 |
| CadEval | 64% | 56% |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Gemini 2.5 Pro leads
Gemini 2.5 Pro: 29.2 (#88), o1: 24.6 (#117)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| METR Time Horizons | 55.4% | 51.1% |
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Too close to call
Gemini 2.5 Pro: 28.8 (#99), o1: 27.9 (#111)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| SimpleBench | 62.4% | 41.7% |
| ARC-AGI-1 | 41% | 30.7% |
| Chess Puzzles | 20% | 15% |
| EnigmaEval | 5.6% | 5.7% |
| LiveBench Reasoning | 89.8% | 91.6% |
| LMArena Hard Prompts | 1455 | 1371 |
| DTBench | 82.4% | 74.7% |
| LiveBench Data Analysis | 79.9% | 65.5% |
| LMCA | 34.8% | 22.3% |
| Epoch Capabilities Index | 145.32 | 141.91 |
| LiveBench | 82.3% | 75.7% |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 70.3% | — |
| CritPt | 2% | — |
| ForecastBench | 61.3 | — |
Math o1 leads
Gemini 2.5 Pro: 32.5 (#213), o1: 36.1 (#175)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 14.7% |
| OTIS Mock AIME 2024-2025 | 84.7% | 73.3% |
| LiveBench Math | 90.2% | 80.3% |
| LMArena Math | 1450 | 1388 |
| MATH Level 5 | 95.9% | 94.7% |
| FrontierMath (Feb 2025 set) | 14.1% | 9.3% |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | 41.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), o1: 41.5 (#110)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| GPQA Diamond | 85.3% | 76.8% |
| Humanity's Last Exam | 21.6% | 8% |
| Confabulations | 10.6% | 11.7% |
| LMArena Expert | 1452 | 1361 |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), o1: 34.2 (#93)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| LMArena Vision | 1263 | 1168 |
| GeoBench | 86% | 80% |
| VPCT | 48% | 37% |
| SpatialViz-Bench | 44.7% | 41.4% |
| LMArena Document | 1421 | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), o1: 48.6 (#142)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| LMArena Non-English | 1451 | 1358 |
| LMArena Chinese | 1507 | 1394 |
| LMArena French | 1472 | 1344 |
| LMArena German | 1487 | 1337 |
| LMArena Japanese | 1461 | 1346 |
| LMArena Korean | 1434 | 1396 |
| LMArena Russian | 1461 | 1356 |
| LMArena Spanish | 1473 | 1345 |
Instruction Following Too close to call
Gemini 2.5 Pro: 75.0 (#75), o1: 74.8 (#86)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| LiveBench Instruction Following | 80.6% | 81.5% |
| LMArena Instruction Following | 1437 | 1367 |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), o1: 50.3 (#9)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| Fiction.LiveBench | 91.7% | 83.3% |
| LMArena Longer Query | 1449 | 1378 |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.7 (#62), o1: 55.6 (#144)
| Benchmark | Gemini 2.5 Pro | o1 |
|---|---|---|
| LMArena Text | 1458 | 1366 |
| LMArena Creative Writing | 1454 | 1348 |
| Short-Story Creative Writing | 83.8% | 70.2% |
| LMArena Multi-Turn | 1453 | 1369 |
| LiveBench Language | 67.8% | 65.4% |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than o1?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 40.9 on the Noometry Index.
Which is cheaper, Gemini 2.5 Pro or o1?
Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; o1 lists at $15 and $60.
Is Gemini 2.5 Pro or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 2.5 Pro and o1 share?
48 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and o1 has 52.