Model comparison
Gemini 2.0 Flash-Lite vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 37.8 on the Noometry Index.
Last verified . 1 shared benchmarks.
GoogleSummary
- They share 1 benchmark with published results for both. Gemini 2.0 Flash-Lite scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 40.1.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemini 2.0 Flash-Lite and 86.9% for o3-pro.
Side by side
| Gemini 2.0 Flash-Lite | o3-pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 42.9 |
| Released | 2025-02-05 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 32 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Gemini 2.0 Flash-Lite: 37.9 (#185), o3-pro: 55.5 (#24)
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| LiveBench Coding | 47.1% | — |
| LMArena Coding | 1322 | — |
Reasoning o3-pro leads
Gemini 2.0 Flash-Lite: 22.0 (#210), o3-pro: 23.8 (#171)
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| DTBench | 52.5% | 86.9% |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| LiveBench Reasoning | 50.1% | — |
| LMArena Hard Prompts | 1324 | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
| ForecastBench | 57.1 | — |
| LiveBench | 54.3% | — |
Math Not comparable
Gemini 2.0 Flash-Lite: 34.1 (#196), o3-pro: —
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
| LMArena Math | 1309 | — |
Knowledge Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 35.0 (#189), o3-pro: 29.5 (#238)
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| MMLU-Pro | 72% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| GPQA (HELM) | 50% | — |
| LMArena Expert | 1305 | — |
Multimodal Not comparable
Gemini 2.0 Flash-Lite: 31.2 (#109), o3-pro: —
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Vision | 1100 | — |
Multilingual Not comparable
Gemini 2.0 Flash-Lite: 46.0 (#161), o3-pro: —
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Non-English | 1323 | — |
| LMArena Chinese | 1339 | — |
| LMArena French | 1347 | — |
| LMArena German | 1306 | — |
| LMArena Japanese | 1301 | — |
| LMArena Korean | 1325 | — |
| LMArena Russian | 1328 | — |
| LMArena Spanish | 1313 | — |
Instruction Following Not comparable
Gemini 2.0 Flash-Lite: 70.4 (#163), o3-pro: —
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
| LMArena Instruction Following | 1305 | — |
Long Context o3-pro leads
Gemini 2.0 Flash-Lite: 40.1 (#160), o3-pro: 72.2 (#1)
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1320 | — |
Writing & Preference o3-pro leads
Gemini 2.0 Flash-Lite: 51.7 (#177), o3-pro: 57.1 (#133)
| Benchmark | Gemini 2.0 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Text | 1330 | — |
| LMArena Creative Writing | 1319 | — |
| Short-Story Creative Writing | — | 84.4% |
| WildBench | 79% | — |
| LMArena Multi-Turn | 1307 | — |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 37.8 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and o3-pro share?
1 benchmark has published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and o3-pro has 12.