Model comparison
Claude Sonnet 5.5 vs Step 5 Preview
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 47.9 on the Noometry Index. Step 5 Preview costs 2.8× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 9 categories and Step 5 Preview in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 46.1.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
- Step 5 Preview accepts more context: 1.02M tokens versus 1M.
Side by side
| Claude Sonnet 5.5 | Step 5 Preview | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 61.9 | 47.9 |
| Released | 2026-09-28 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.02M |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $10 | $2.70 |
| Results tracked | 32 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 67.3 (#6), Step 5 Preview: 51.8 (#36)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1774 | 1564 |
| SciCode | 61% | 58.9% |
| LMArena Coding | 1513 | 1480 |
| FrontierCode | 52.1% | — |
| CursorBench | 55.5% | — |
| FrontierSWE | 61.9% | — |
| ALE-Bench | 1,819 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5.5: 45.0 (#16), Step 5 Preview: —
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| APEX-Agents | 75.5% | — |
Reasoning Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 54.0 (#28), Step 5 Preview: 40.0 (#57)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| CritPt | 31.4% | 20.9% |
| LMArena Hard Prompts | 1495 | 1465 |
| NYT Connections (extended) | 80.5% | — |
| Mystery Game Puzzles | 65% | — |
| Epoch Capabilities Index | 165.03 | — |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 87.9 (#6), Step 5 Preview: 46.1 (#72)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| ProofBench | 100% | 42% |
| LMArena Math | 1510 | 1470 |
| FrontierMath (Tiers 1-3) | 88.8% | — |
| FrontierMath Tier 4 | 80.5% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#12), Step 5 Preview: 41.2 (#112)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1540 | 1470 |
| GPQA Diamond | 95.6% | — |
| SimpleQA Verified | 46.5% | — |
Multimodal Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 51.5 (#6), Step 5 Preview: 41.0 (#41)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1289 | 1267 |
| Furniture Assembly | 75% | — |
Multilingual Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 55.3 (#30), Step 5 Preview: 53.8 (#54)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1452 | 1432 |
| LMArena Chinese | 1522 | 1519 |
| LMArena Russian | 1451 | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 78.3 (#11), Step 5 Preview: 76.0 (#50)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1495 | 1444 |
Long Context Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 45.9 (#28), Step 5 Preview: 44.5 (#64)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1498 | 1455 |
Writing & Preference Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#40), Step 5 Preview: 62.8 (#71)
| Benchmark | Claude Sonnet 5.5 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1471 | 1442 |
| LMArena Creative Writing | 1465 | 1410 |
| LMArena Multi-Turn | 1474 | 1447 |
Frequently asked questions
Is Claude Sonnet 5.5 better than Step 5 Preview?
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 47.9 on the Noometry Index. Step 5 Preview costs 2.8× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5.5 or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.
Is Claude Sonnet 5.5 or Step 5 Preview better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 51.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 1M.
How many benchmarks do Claude Sonnet 5.5 and Step 5 Preview share?
17 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Step 5 Preview has 18.