Model comparison
Gemini 3.1 Flash Lite vs o3-mini
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 36.7 on the Noometry Index.
Last verified . 28 shared benchmarks.
GoogleSummary
- They share 28 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 7 categories and o3-mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Flash Lite leads 40.7 to 28.1.
- The biggest single-benchmark swing is LMCA: 35% for Gemini 3.1 Flash Lite and 19% for o3-mini.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 3.1 Flash Lite | o3-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 40.8 | 36.7 |
| Released | 2026-03-03 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.25 | $1.10 |
| Output $ / M tokens | $1.50 | $4.40 |
| Results tracked | 38 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Gemini 3.1 Flash Lite: 37.8 (#188), o3-mini: 40.8 (#132)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| SciCode | 41.9% | 39.8% |
| WeirdML | 52.2% | 43.7% |
| LMArena Coding | 1400 | 1378 |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1256 | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Too close to call
Gemini 3.1 Flash Lite: 30.2 (#79), o3-mini: 29.6 (#84)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
| DeepResearch Bench | 37.3% | — |
Reasoning Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 22.9 (#186), o3-mini: 16.3 (#305)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| CritPt | 1.1% | 0.3% |
| Chess Puzzles | 25% | 17% |
| LMArena Hard Prompts | 1407 | 1366 |
| DTBench | 76.8% | 68.8% |
| LMCA | 35% | 19% |
| Epoch Capabilities Index | 144.47 | 140.34 |
| ForecastBench | 54.4 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 67.2% | — |
| NYT Connections (extended) | 8.2% | — |
| ARC-AGI-1 | — | 34.5% |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), o3-mini: 28.1 (#244)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 18.6% |
| OTIS Mock AIME 2024-2025 | 80% | 76.9% |
| LMArena Math | 1428 | 1396 |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.9 (#104), o3-mini: 38.3 (#146)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| GPQA Diamond | 81.8% | 77% |
| LMArena Expert | 1398 | 1364 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), o3-mini: —
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), o3-mini: 45.7 (#164)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| LMArena Non-English | 1411 | 1319 |
| LMArena Chinese | 1461 | 1379 |
| LMArena French | 1424 | 1334 |
| LMArena German | 1429 | 1303 |
| LMArena Japanese | 1413 | 1286 |
| LMArena Korean | 1392 | 1314 |
| LMArena Russian | 1420 | 1304 |
| LMArena Spanish | 1421 | 1321 |
Instruction Following o3-mini leads
Gemini 3.1 Flash Lite: 72.7 (#131), o3-mini: 75.1 (#72)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1377 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#122), o3-mini: 33.8 (#256)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| LMArena Longer Query | 1394 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 60.9 (#94), o3-mini: 50.3 (#182)
| Benchmark | Gemini 3.1 Flash Lite | o3-mini |
|---|---|---|
| LMArena Text | 1416 | 1337 |
| LMArena Creative Writing | 1401 | 1286 |
| LMArena Multi-Turn | 1417 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than o3-mini?
Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 36.7 on the Noometry Index.
Which is cheaper, Gemini 3.1 Flash Lite or o3-mini?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Gemini 3.1 Flash Lite or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 3.1 Flash Lite and o3-mini share?
28 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and o3-mini has 51.