Model comparison
Claude 3.7 Sonnet vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Step 5 Preview in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 18.6.
Side by side
| Claude 3.7 Sonnet | Step 5 Preview | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 39.5 | 47.9 |
| Released | 2025-02-24 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 58 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Claude 3.7 Sonnet: 40.6 (#136), Step 5 Preview: 51.8 (#36)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1361 | 1480 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 34.1 (#50), Step 5 Preview: —
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Step 5 Preview leads
Claude 3.7 Sonnet: 18.6 (#277), Step 5 Preview: 40.0 (#57)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1465 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 20.9% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Step 5 Preview leads
Claude 3.7 Sonnet: 37.5 (#153), Step 5 Preview: 46.1 (#72)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Math | 1337 | 1470 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 42% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Step 5 Preview leads
Claude 3.7 Sonnet: 39.8 (#130), Step 5 Preview: 41.2 (#112)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1321 | 1470 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Step 5 Preview leads
Claude 3.7 Sonnet: 33.7 (#95), Step 5 Preview: 41.0 (#41)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1169 | 1267 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Step 5 Preview leads
Claude 3.7 Sonnet: 44.1 (#179), Step 5 Preview: 53.8 (#54)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1296 | 1432 |
| LMArena Chinese | 1299 | 1519 |
| LMArena Russian | 1311 | 1436 |
| LMArena Spanish | 1298 | 1439 |
| LMArena French | 1303 | — |
| LMArena German | 1301 | — |
| LMArena Japanese | 1267 | — |
| LMArena Korean | 1249 | — |
Instruction Following Step 5 Preview leads
Claude 3.7 Sonnet: 72.9 (#125), Step 5 Preview: 76.0 (#50)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1352 | 1444 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Step 5 Preview: 44.5 (#64)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1373 | 1455 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Step 5 Preview leads
Claude 3.7 Sonnet: 54.4 (#150), Step 5 Preview: 62.8 (#71)
| Benchmark | Claude 3.7 Sonnet | Step 5 Preview |
|---|---|---|
| LMArena Text | 1314 | 1442 |
| LMArena Creative Writing | 1332 | 1410 |
| LMArena Multi-Turn | 1339 | 1447 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Step 5 Preview share?
14 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Step 5 Preview has 18.