Model comparison
Gemini 3.1 Flash Lite vs o4-mini
Gemini 3.1 Flash Lite and o4-mini score almost the same on the Noometry Index (40.8 vs 41.6), so choose on price, context window or the category you care about most.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 2 categories and o4-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 54.0.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 8.2% for Gemini 3.1 Flash Lite and 18.6% for o4-mini.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 3.1 Flash Lite | o4-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 40.8 | 41.6 |
| Released | 2026-03-03 | 2025-04-16 |
| 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 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Gemini 3.1 Flash Lite: 37.8 (#188), o4-mini: 40.9 (#127)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| WeirdML | 52.2% | 52.6% |
| LMArena Coding | 1400 | 1368 |
| ALE-Bench | 797.73 | 826.17 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Gemini 3.1 Flash Lite: 30.2 (#79), o4-mini: 32.6 (#61)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| DeepResearch Bench | 37.3% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Gemini 3.1 Flash Lite: 22.9 (#186), o4-mini: 24.6 (#162)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 67.6% |
| CritPt | 1.1% | 0.6% |
| Chess Puzzles | 25% | 26% |
| EnigmaEval | 3% | 9.2% |
| LMArena Hard Prompts | 1407 | 1351 |
| DTBench | 76.8% | 77.6% |
| LMCA | 35% | 26.5% |
| Epoch Capabilities Index | 144.47 | 145.64 |
| ForecastBench | 54.4 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| NYT Connections (extended) | 8.2% | — |
| ARC-AGI-1 | — | 58.7% |
| Thematic Generalization | 63.3% | — |
| Mystery Game Puzzles | — | 5% |
Math Too close to call
Gemini 3.1 Flash Lite: 40.7 (#90), o4-mini: 40.8 (#89)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 36.1% |
| OTIS Mock AIME 2024-2025 | 80% | 81.7% |
| LMArena Math | 1428 | 1389 |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Gemini 3.1 Flash Lite: 41.9 (#104), o4-mini: 43.6 (#91)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| GPQA Diamond | 81.8% | 79.6% |
| Humanity's Last Exam | 8.6% | 18.1% |
| Vectara Hallucination Rate | 8.2% | 18.6% |
| LMArena Expert | 1398 | 1343 |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Too close to call
Gemini 3.1 Flash Lite: 39.4 (#60), o4-mini: 40.2 (#49)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| LMArena Vision | 1240 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), o4-mini: 47.0 (#154)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| LMArena Non-English | 1411 | 1337 |
| LMArena Chinese | 1461 | 1354 |
| LMArena French | 1424 | 1364 |
| LMArena German | 1429 | 1336 |
| LMArena Japanese | 1413 | 1308 |
| LMArena Korean | 1392 | 1312 |
| LMArena Russian | 1420 | 1334 |
| LMArena Spanish | 1421 | 1347 |
Instruction Following o4-mini leads
Gemini 3.1 Flash Lite: 72.7 (#131), o4-mini: 75.2 (#68)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1377 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Gemini 3.1 Flash Lite: 42.5 (#122), o4-mini: 45.5 (#33)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| LMArena Longer Query | 1394 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 60.9 (#94), o4-mini: 54.0 (#152)
| Benchmark | Gemini 3.1 Flash Lite | o4-mini |
|---|---|---|
| LMArena Text | 1416 | 1353 |
| LMArena Creative Writing | 1401 | 1294 |
| LMArena Multi-Turn | 1417 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than o4-mini?
Gemini 3.1 Flash Lite and o4-mini score almost the same on the Noometry Index (40.8 vs 41.6), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 3.1 Flash Lite or o4-mini?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Gemini 3.1 Flash Lite or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 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 o4-mini share?
33 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and o4-mini has 60.