Model comparison
Gemini 2.0 Flash (Feb 2025) vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 35.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
StepFunSummary
- They share 17 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 4 categories and Step 3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 15.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Gemini 2.0 Flash (Feb 2025) and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 35.1 | 40.5 |
| Released | 2024-12-06 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Step 3: 40.1 (#147)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Coding | 1350 | 1367 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Step 3: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Step 3 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Step 3: 28.4 (#105)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 62.3% |
| LMArena Hard Prompts | 1346 | 1355 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| Epoch Capabilities Index | 135.36 | — |
| LiveBench | 66.9% | — |
Math Too close to call
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Step 3: 37.6 (#148)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Math | 1352 | 1366 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Step 3 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Step 3: 36.8 (#164)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Expert | 1339 | 1333 |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Step 3: 35.5 (#86)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Vision | 1158 | 1177 |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Step 3: 46.3 (#159)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Non-English | 1342 | 1327 |
| LMArena Chinese | 1373 | 1397 |
| LMArena German | 1353 | 1371 |
| LMArena Korean | 1313 | 1269 |
| LMArena Russian | 1351 | 1331 |
| LMArena Spanish | 1363 | 1371 |
| LMArena French | 1391 | — |
| LMArena Japanese | 1294 | — |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Step 3: 70.4 (#164)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1336 | 1332 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Step 3 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Step 3: 40.3 (#157)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Longer Query | 1344 | 1326 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Step 3 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Step 3: 54.3 (#151)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 3 |
|---|---|---|
| LMArena Text | 1354 | 1350 |
| LMArena Creative Writing | 1340 | 1321 |
| LMArena Multi-Turn | 1350 | 1341 |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Step 3 share?
17 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Step 3 has 17.