Model comparison
Gemini 2.0 Flash (Feb 2025) vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 35.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
StepFunSummary
- They share 14 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 15.2.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Step 5 Preview | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 35.1 | 47.9 |
| Released | 2024-12-06 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 54 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Step 5 Preview: 51.8 (#36)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1350 | 1480 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| 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 5 Preview: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Step 5 Preview: 40.0 (#57)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1346 | 1465 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | — | 20.9% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| Epoch Capabilities Index | 135.36 | — |
| LiveBench | 66.9% | — |
Math Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Step 5 Preview: 46.1 (#72)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Math | 1352 | 1470 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 42% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Step 5 Preview: 41.2 (#112)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1339 | 1470 |
| 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 Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Step 5 Preview: 41.0 (#41)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1158 | 1267 |
| GeoBench | 77% | — |
Multilingual Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Step 5 Preview: 53.8 (#54)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1342 | 1432 |
| LMArena Chinese | 1373 | 1519 |
| LMArena Russian | 1351 | 1436 |
| LMArena Spanish | 1363 | 1439 |
| LMArena French | 1391 | — |
| LMArena German | 1353 | — |
| LMArena Japanese | 1294 | — |
| LMArena Korean | 1313 | — |
Instruction Following Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Step 5 Preview: 76.0 (#50)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1336 | 1444 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Step 5 Preview: 44.5 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1344 | 1455 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Step 5 Preview leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Step 5 Preview: 62.8 (#71)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Step 5 Preview |
|---|---|---|
| LMArena Text | 1354 | 1442 |
| LMArena Creative Writing | 1340 | 1410 |
| LMArena Multi-Turn | 1350 | 1447 |
| 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 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Step 5 Preview share?
14 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Step 5 Preview has 18.