Model comparison
Gemini 2.0 Flash-Lite vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 37.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
StepFunSummary
- They share 16 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and Step 3 in 9 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 22.0.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash-Lite | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 37.8 | 40.5 |
| Released | 2025-02-05 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemini 2.0 Flash-Lite: 37.9 (#185), Step 3: 40.1 (#147)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Coding | 1322 | 1367 |
| LiveBench Coding | 47.1% | — |
Reasoning Step 3 leads
Gemini 2.0 Flash-Lite: 22.0 (#210), Step 3: 28.4 (#105)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 50.1% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 65.5% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 54.3% | — |
Math Step 3 leads
Gemini 2.0 Flash-Lite: 34.1 (#196), Step 3: 37.6 (#148)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Math | 1309 | 1366 |
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
Knowledge Step 3 leads
Gemini 2.0 Flash-Lite: 35.0 (#189), Step 3: 36.8 (#164)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Expert | 1305 | 1333 |
| MMLU-Pro | 72% | — |
| GPQA (HELM) | 50% | — |
Multimodal Step 3 leads
Gemini 2.0 Flash-Lite: 31.2 (#109), Step 3: 35.5 (#86)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Vision | 1100 | 1177 |
Multilingual Too close to call
Gemini 2.0 Flash-Lite: 46.0 (#161), Step 3: 46.3 (#159)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Non-English | 1323 | 1327 |
| LMArena Chinese | 1339 | 1397 |
| LMArena German | 1306 | 1371 |
| LMArena Korean | 1325 | 1269 |
| LMArena Russian | 1328 | 1331 |
| LMArena Spanish | 1313 | 1371 |
| LMArena French | 1347 | — |
| LMArena Japanese | 1301 | — |
Instruction Following Too close to call
Gemini 2.0 Flash-Lite: 70.4 (#163), Step 3: 70.4 (#164)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1305 | 1332 |
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
Long Context Too close to call
Gemini 2.0 Flash-Lite: 40.1 (#160), Step 3: 40.3 (#157)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Longer Query | 1320 | 1326 |
Writing & Preference Step 3 leads
Gemini 2.0 Flash-Lite: 51.7 (#177), Step 3: 54.3 (#151)
| Benchmark | Gemini 2.0 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Text | 1330 | 1350 |
| LMArena Creative Writing | 1319 | 1321 |
| LMArena Multi-Turn | 1307 | 1341 |
| WildBench | 79% | — |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 37.8 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and Step 3 share?
16 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and Step 3 has 17.