Model comparison
Gemini 3 Flash Preview vs o1
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 40.9 on the Noometry Index.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and o1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 27.9.
- The biggest single-benchmark swing is ARC-AGI-1: 84.7% for Gemini 3 Flash Preview and 30.7% for o1.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $15 / $60 for o1.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 3 Flash Preview | o1 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 52.3 | 40.9 |
| Released | 2025-12-17 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.50 | $15 |
| Output $ / M tokens | $3 | $60 |
| Results tracked | 59 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 50.9 (#42), o1: 46.1 (#70)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| WeirdML | 61.6% | 47.6% |
| LMArena Coding | 1460 | 1367 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| ALE-Bench | 1,367 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 38.7 (#29), o1: 24.6 (#117)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| Cybench | — | 10% |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| METR Time Horizons | — | 51.1% |
| Vending-Bench 2 | 3,635 | — |
Reasoning Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 49.2 (#37), o1: 27.9 (#111)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| SimpleBench | 61.1% | 41.7% |
| ARC-AGI-1 | 84.7% | 30.7% |
| Chess Puzzles | 40% | 15% |
| LMArena Hard Prompts | 1465 | 1371 |
| DTBench | 89.1% | 74.7% |
| LMCA | 43.1% | 22.3% |
| Epoch Capabilities Index | 151.8 | 141.91 |
| ARC-AGI-2 | 33.6% | — |
| NYT Connections (extended) | 83.1% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 26% | — |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 58.5 | — |
| LiveBench | — | 75.7% |
Math Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 51.7 (#55), o1: 36.1 (#175)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 14.7% |
| OTIS Mock AIME 2024-2025 | 95.6% | 73.3% |
| LMArena Math | 1473 | 1388 |
| FrontierMath (Feb 2025 set) | 35.6% | 9.3% |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 15% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 58.8 (#33), o1: 41.5 (#110)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| GPQA Diamond | 89.4% | 76.8% |
| SimpleQA Verified | 66.8% | 41.1% |
| LMArena Expert | 1462 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 13.5% | — |
Multimodal Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 45.5 (#16), o1: 34.2 (#93)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| LMArena Vision | 1285 | 1168 |
| GeoBench | 88% | 80% |
| VPCT | 72.6% | 37% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 55.7 (#27), o1: 48.6 (#142)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| LMArena Non-English | 1458 | 1358 |
| LMArena Chinese | 1511 | 1394 |
| LMArena French | 1477 | 1344 |
| LMArena German | 1497 | 1337 |
| LMArena Japanese | 1489 | 1346 |
| LMArena Korean | 1443 | 1396 |
| LMArena Russian | 1480 | 1356 |
| LMArena Spanish | 1469 | 1345 |
Instruction Following Too close to call
Gemini 3 Flash Preview: 75.7 (#56), o1: 74.8 (#86)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Gemini 3 Flash Preview: 44.4 (#67), o1: 50.3 (#9)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| LMArena Longer Query | 1452 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 3 Flash Preview: 65.5 (#45), o1: 55.6 (#144)
| Benchmark | Gemini 3 Flash Preview | o1 |
|---|---|---|
| LMArena Text | 1466 | 1366 |
| LMArena Creative Writing | 1457 | 1348 |
| LMArena Multi-Turn | 1471 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Gemini 3 Flash Preview better than o1?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 40.9 on the Noometry Index.
Which is cheaper, Gemini 3 Flash Preview or o1?
Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; o1 lists at $15 and $60.
Is Gemini 3 Flash Preview or o1 better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3 Flash Preview does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 3 Flash Preview and o1 share?
32 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and o1 has 52.