Model comparison
Gemini 2.5 Flash-Lite vs o3-pro
o3-pro is the stronger model overall, scoring 42.7 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 200× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
GoogleSummary
- They share 7 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and o3-pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 33.3.
- The biggest single-benchmark swing is Fiction.LiveBench: 47.2% for Gemini 2.5 Flash-Lite and 97.2% for o3-pro.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $20 / $80 for o3-pro.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 2.5 Flash-Lite | o3-pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 36.4 | 42.7 |
| Released | 2025-06-17 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.10 | $20 |
| Output $ / M tokens | $0.40 | $80 |
| Results tracked | 33 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Gemini 2.5 Flash-Lite: 38.0 (#167), o3-pro: 55.1 (#22)
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| WeirdML | 35.2% | 58.2% |
| Aider Polyglot | — | 84.9% |
| LMArena Coding | 1373 | — |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash-Lite: 27.8 (#89), o3-pro: —
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
Reasoning o3-pro leads
Gemini 2.5 Flash-Lite: 21.5 (#196), o3-pro: 24.1 (#152)
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 72.1% |
| DTBench | 62.8% | 86.9% |
| LMCA | 18.1% | 38.5% |
| Epoch Capabilities Index | 133.93 | 147.43 |
| ARC-AGI-2 | — | 4.9% |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1377 | — |
Math Not comparable
Gemini 2.5 Flash-Lite: 35.5 (#144), o3-pro: —
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| Omni-MATH | 48% | — |
| LMArena Math | 1373 | — |
Knowledge Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 32.1 (#206), o3-pro: 29.0 (#234)
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 23.3% |
| MMLU-Pro | 53.7% | — |
| Confabulations | — | 14.2% |
| GPQA (HELM) | 30.9% | — |
| LMArena Expert | 1373 | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), o3-pro: —
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Not comparable
Gemini 2.5 Flash-Lite: 49.5 (#129), o3-pro: —
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Non-English | 1369 | — |
| LMArena Chinese | 1404 | — |
| LMArena French | 1388 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1359 | — |
| LMArena Korean | 1358 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1396 | — |
Instruction Following Not comparable
Gemini 2.5 Flash-Lite: 70.2 (#163), o3-pro: —
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| IFEval | 81% | — |
| LMArena Instruction Following | 1366 | — |
Long Context o3-pro leads
Gemini 2.5 Flash-Lite: 33.3 (#257), o3-pro: 72.1 (#1)
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| Fiction.LiveBench | 47.2% | 97.2% |
| LMArena Longer Query | 1373 | — |
Writing & Preference Too close to call
Gemini 2.5 Flash-Lite: 57.0 (#130), o3-pro: 57.1 (#128)
| Benchmark | Gemini 2.5 Flash-Lite | o3-pro |
|---|---|---|
| LMArena Text | 1379 | — |
| LMArena Creative Writing | 1366 | — |
| Short-Story Creative Writing | — | 84.4% |
| WildBench | 81.8% | — |
| LMArena Multi-Turn | 1367 | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than o3-pro?
o3-pro is the stronger model overall, scoring 42.7 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 200× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or o3-pro?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; o3-pro lists at $20 and $80.
Is Gemini 2.5 Flash-Lite or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 200K.
How many benchmarks do Gemini 2.5 Flash-Lite and o3-pro share?
7 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and o3-pro has 12.