Model comparison
Claude Sonnet 4 vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Claude Sonnet 4 scores higher in 4 categories and Step 3.5 Flash in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Step 3.5 Flash leads 42.8 to 33.7.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Step 3.5 Flash accepts more context: 256K tokens versus 200K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Step 3.5 Flash | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 40.8 | 42.3 |
| Released | 2025-05-22 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 64K | 256K |
| Input $ / M tokens | $3 | $0.10 |
| Output $ / M tokens | $15 | $0.30 |
| Results tracked | 58 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1414 | 1436 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Step 3.5 Flash: —
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Too close to call
Claude Sonnet 4: 22.9 (#187), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1411 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Too close to call
Claude Sonnet 4: 43.3 (#80), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1375 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1372 | 1421 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Step 3.5 Flash: —
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Step 3.5 Flash leads
Claude Sonnet 4: 46.7 (#156), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1333 | 1385 |
| LMArena Chinese | 1350 | 1447 |
| LMArena French | 1363 | 1421 |
| LMArena German | 1331 | 1405 |
| LMArena Japanese | 1302 | 1354 |
| LMArena Korean | 1291 | 1352 |
| LMArena Russian | 1355 | 1385 |
| LMArena Spanish | 1357 | 1419 |
Instruction Following Step 3.5 Flash leads
Claude Sonnet 4: 71.7 (#145), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1376 | 1385 |
| IFEval | 84% | — |
Long Context Step 3.5 Flash leads
Claude Sonnet 4: 33.7 (#259), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1398 | 1402 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Step 3.5 Flash leads
Claude Sonnet 4: 57.1 (#132), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Claude Sonnet 4 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1351 | 1403 |
| LMArena Creative Writing | 1345 | 1357 |
| LMArena Multi-Turn | 1376 | 1405 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.8 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Step 3.5 Flash better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Step 3.5 Flash share?
17 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Step 3.5 Flash has 19.