Model comparison
Gemini 2.0 Flash-Lite vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 37.8 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and o4-mini in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where o4-mini leads 40.2 to 31.2.
- The biggest single-benchmark swing is Omni-MATH: 37.4% for Gemini 2.0 Flash-Lite and 72% for o4-mini.
Side by side
| Gemini 2.0 Flash-Lite | o4-mini | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 41.6 |
| Released | 2025-02-05 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 32 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Gemini 2.0 Flash-Lite: 37.9 (#185), o4-mini: 40.9 (#127)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Coding | 1322 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| LiveBench Coding | 47.1% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, o4-mini: 32.6 (#61)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Gemini 2.0 Flash-Lite: 22.0 (#210), o4-mini: 24.6 (#162)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1351 |
| DTBench | 52.5% | 77.6% |
| ForecastBench | 57.1 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| LiveBench | 54.3% | — |
Math o4-mini leads
Gemini 2.0 Flash-Lite: 34.1 (#196), o4-mini: 40.8 (#89)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| Omni-MATH | 37.4% | 72% |
| LMArena Math | 1309 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Gemini 2.0 Flash-Lite: 35.0 (#189), o4-mini: 43.6 (#91)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| MMLU-Pro | 72% | 82% |
| GPQA (HELM) | 50% | 73.5% |
| LMArena Expert | 1305 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
Multimodal o4-mini leads
Gemini 2.0 Flash-Lite: 31.2 (#109), o4-mini: 40.2 (#49)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Vision | 1100 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Too close to call
Gemini 2.0 Flash-Lite: 46.0 (#161), o4-mini: 47.0 (#154)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Non-English | 1323 | 1337 |
| LMArena Chinese | 1339 | 1354 |
| LMArena French | 1347 | 1364 |
| LMArena German | 1306 | 1336 |
| LMArena Japanese | 1301 | 1308 |
| LMArena Korean | 1325 | 1312 |
| LMArena Russian | 1328 | 1334 |
| LMArena Spanish | 1313 | 1347 |
Instruction Following o4-mini leads
Gemini 2.0 Flash-Lite: 70.4 (#163), o4-mini: 75.2 (#68)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| IFEval | 82.4% | 92.8% |
| LMArena Instruction Following | 1305 | 1321 |
| LiveBench Instruction Following | 78.3% | — |
Long Context o4-mini leads
Gemini 2.0 Flash-Lite: 40.1 (#160), o4-mini: 45.5 (#33)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Longer Query | 1320 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Gemini 2.0 Flash-Lite: 51.7 (#177), o4-mini: 54.0 (#152)
| Benchmark | Gemini 2.0 Flash-Lite | o4-mini |
|---|---|---|
| LMArena Text | 1330 | 1353 |
| LMArena Creative Writing | 1319 | 1294 |
| WildBench | 79% | 85.4% |
| LMArena Multi-Turn | 1307 | 1350 |
| Short-Story Creative Writing | — | 75% |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 37.8 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and o4-mini share?
25 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and o4-mini has 60.