Model comparison
Gemini 3.1 Flash Lite vs o3
o3 is the stronger model overall, scoring 47.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 6.2× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 1 category and o3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 41.9.
- The biggest single-benchmark swing is Chess Puzzles: 25% for Gemini 3.1 Flash Lite and 38% for o3.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $2 / $8 for o3.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 200K.
Side by side
| Gemini 3.1 Flash Lite | o3 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 40.8 | 47.5 |
| Released | 2026-03-03 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $0.25 | $2 |
| Output $ / M tokens | $1.50 | $8 |
| Results tracked | 38 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Gemini 3.1 Flash Lite: 37.8 (#188), o3: 46.8 (#64)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| WeirdML | 52.2% | 52.4% |
| LMArena Coding | 1400 | 1408 |
| ALE-Bench | 797.73 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |
Agentic & Tool Use o3 leads
Gemini 3.1 Flash Lite: 30.2 (#79), o3: 34.5 (#44)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| DeepResearch Bench | 37.3% | 45.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Gemini 3.1 Flash Lite: 22.9 (#186), o3: 32.0 (#78)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 67.6% |
| CritPt | 1.1% | 1.4% |
| Chess Puzzles | 25% | 38% |
| EnigmaEval | 3% | 13.1% |
| LMArena Hard Prompts | 1407 | 1402 |
| DTBench | 76.8% | 84.8% |
| LMCA | 35% | 39.7% |
| Epoch Capabilities Index | 144.47 | 146.86 |
| ForecastBench | 54.4 | 62.5 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| NYT Connections (extended) | 8.2% | — |
| ARC-AGI-1 | — | 60.8% |
| Thematic Generalization | 63.3% | — |
| Mystery Game Puzzles | — | 29% |
Math o3 leads
Gemini 3.1 Flash Lite: 40.7 (#90), o3: 50.2 (#58)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 33.3% |
| OTIS Mock AIME 2024-2025 | 80% | 84.4% |
| LMArena Math | 1428 | 1426 |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Gemini 3.1 Flash Lite: 41.9 (#104), o3: 54.6 (#52)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| GPQA Diamond | 81.8% | 81.8% |
| Humanity's Last Exam | 8.6% | 20.3% |
| LMArena Expert | 1398 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | — | 75.3% |
Multimodal o3 leads
Gemini 3.1 Flash Lite: 39.4 (#60), o3: 41.4 (#36)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| LMArena Vision | 1240 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Too close to call
Gemini 3.1 Flash Lite: 52.3 (#86), o3: 51.7 (#105)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| LMArena Non-English | 1411 | 1401 |
| LMArena Chinese | 1461 | 1437 |
| LMArena French | 1424 | 1430 |
| LMArena German | 1429 | 1420 |
| LMArena Japanese | 1413 | 1403 |
| LMArena Korean | 1392 | 1370 |
| LMArena Russian | 1420 | 1406 |
| LMArena Spanish | 1421 | 1395 |
Instruction Following Too close to call
Gemini 3.1 Flash Lite: 72.7 (#131), o3: 72.8 (#127)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| LMArena Instruction Following | 1377 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Gemini 3.1 Flash Lite: 42.5 (#122), o3: 53.3 (#6)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| LMArena Longer Query | 1394 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Gemini 3.1 Flash Lite: 60.9 (#94), o3: 63.5 (#64)
| Benchmark | Gemini 3.1 Flash Lite | o3 |
|---|---|---|
| LMArena Text | 1416 | 1410 |
| LMArena Creative Writing | 1401 | 1359 |
| LMArena Multi-Turn | 1417 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than o3?
o3 is the stronger model overall, scoring 47.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 6.2× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or o3?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; o3 lists at $2 and $8.
Is Gemini 3.1 Flash Lite or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 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 share?
33 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and o3 has 63.