Model comparison
Gemini 3.1 Flash Lite vs Step 3
Gemini 3.1 Flash Lite and Step 3 score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 7 categories and Step 3 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 40.8 | 40.5 |
| Released | 2026-03-03 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 38 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemini 3.1 Flash Lite: 37.8 (#188), Step 3: 40.1 (#147)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Coding | 1400 | 1367 |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| WeirdML | 52.2% | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 30.2 (#79), Step 3: —
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Step 3 leads
Gemini 3.1 Flash Lite: 22.9 (#186), Step 3: 28.4 (#105)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 62.3% |
| LMArena Hard Prompts | 1407 | 1355 |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| Epoch Capabilities Index | 144.47 | — |
| ForecastBench | 54.4 | — |
Math Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 40.7 (#90), Step 3: 37.6 (#148)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Math | 1428 | 1366 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.9 (#104), Step 3: 36.8 (#164)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Expert | 1398 | 1333 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 8.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.4 (#60), Step 3: 35.5 (#86)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Vision | 1240 | 1177 |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), Step 3: 46.3 (#159)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Non-English | 1411 | 1327 |
| LMArena Chinese | 1461 | 1397 |
| LMArena German | 1429 | 1371 |
| LMArena Korean | 1392 | 1269 |
| LMArena Russian | 1420 | 1331 |
| LMArena Spanish | 1421 | 1371 |
| LMArena French | 1424 | — |
| LMArena Japanese | 1413 | — |
Instruction Following Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 72.7 (#131), Step 3: 70.4 (#164)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1377 | 1332 |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#122), Step 3: 40.3 (#157)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Longer Query | 1394 | 1326 |
Writing & Preference Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 60.9 (#94), Step 3: 54.3 (#151)
| Benchmark | Gemini 3.1 Flash Lite | Step 3 |
|---|---|---|
| LMArena Text | 1416 | 1350 |
| LMArena Creative Writing | 1401 | 1321 |
| LMArena Multi-Turn | 1417 | 1341 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Step 3?
Gemini 3.1 Flash Lite and Step 3 score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.
Is Gemini 3.1 Flash Lite or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 37.8 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Flash Lite and Step 3 share?
17 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Step 3 has 17.