# Claude 2.1 vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 25.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-step-5-preview
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Step 5 Preview leads 46.1 to 10.2.

## Snapshot

| | Claude 2.1 | Step 5 Preview |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 25.2 | 47.9 |
| Rank | 345 | 58 |
| Context | — | 1.02M |
| Input $/M | — | $1 |
| Output $/M | — | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2.1: 26.2 (#327)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1480 |

## Reasoning

- Claude 2.1: 21.4 (#221)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 10.2 (#315)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |

## Knowledge

- Claude 2.1: 15.4 (#292)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 33% | — |
| LMArena Expert | — | 1470 |
| MMLU | 73.5% | — |

## Multimodal

- Claude 2.1: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Claude 2.1: —
- Step 5 Preview: 53.8 (#54)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Claude 2.1: —
- Step 5 Preview: 76.0 (#50)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |

## Long Context

- Claude 2.1: —
- Step 5 Preview: 44.5 (#64)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |

## Writing & Preference

- Claude 2.1: —
- Step 5 Preview: 62.8 (#71)

| Benchmark | Claude 2.1 | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |

## FAQ

### Is Claude 2.1 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 25.2 on the Noometry Index.

### Is Claude 2.1 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 26.2 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and Step 5 Preview share?

0 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Step 5 Preview has 18.