# Step 5 Preview vs Tulu 3 (Tülu 3) 70B

> Step 5 Preview is the stronger model overall, scoring 47.9 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/step-5-preview-vs-tulu-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Step 5 Preview scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 14.2.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

## Snapshot

| | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | StepFun | Allen Institute for AI (Ai2) |
| Noometry Index | 47.9 | 33.0 |
| Rank | 58 | 251 |
| Context | 1.02M | — |
| Input $/M | $1 | — |
| Output $/M | $2.70 | — |
| Weights | Proprietary | Open |

## Coding

- Step 5 Preview: 51.8 (#36)
- Tulu 3 (Tülu 3) 70B: 36.0 (#214)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1480 | 1235 |
| LMArena WebDev | 1564 | — |
| SciCode | 58.9% | — |

## Reasoning

- Step 5 Preview: 40.0 (#57)
- Tulu 3 (Tülu 3) 70B: 23.9 (#169)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1220 |
| CritPt | 20.9% | — |

## Math

- Step 5 Preview: 46.1 (#72)
- Tulu 3 (Tülu 3) 70B: 14.2 (#303)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1470 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| ProofBench | 42% | — |
| MATH Level 5 | — | 42.7% |

## Knowledge

- Step 5 Preview: 41.2 (#112)
- Tulu 3 (Tülu 3) 70B: 25.0 (#264)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1470 | — |

## Multimodal

- Step 5 Preview: 41.0 (#41)
- Tulu 3 (Tülu 3) 70B: —

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1267 | — |

## Multilingual

- Step 5 Preview: 53.8 (#54)
- Tulu 3 (Tülu 3) 70B: 39.9 (#222)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1432 | 1236 |
| LMArena Chinese | 1519 | 1249 |
| LMArena Russian | 1436 | 1246 |
| LMArena Spanish | 1439 | — |

## Instruction Following

- Step 5 Preview: 76.0 (#50)
- Tulu 3 (Tülu 3) 70B: 64.8 (#227)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1444 | 1233 |

## Long Context

- Step 5 Preview: 44.5 (#64)
- Tulu 3 (Tülu 3) 70B: 37.1 (#222)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1455 | 1224 |

## Writing & Preference

- Step 5 Preview: 62.8 (#71)
- Tulu 3 (Tülu 3) 70B: 45.6 (#223)

| Benchmark | Step 5 Preview | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1442 | 1256 |
| LMArena Creative Writing | 1410 | 1231 |
| LMArena Multi-Turn | 1447 | 1252 |

## FAQ

### Is Step 5 Preview better than Tulu 3 (Tülu 3) 70B?

Step 5 Preview is the stronger model overall, scoring 47.9 to 33.0 on the Noometry Index.

### Is Step 5 Preview or Tulu 3 (Tülu 3) 70B better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 36.0 in the Noometry coding category.

### How many benchmarks do Step 5 Preview and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Step 5 Preview has 18 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.