# Step 5 Preview vs Yi-34B

> Step 5 Preview is the stronger model overall, scoring 47.9 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/step-5-preview-vs-yi-34b
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Step 5 Preview scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 5 Preview leads 41.2 to 7.5.
- Yi-34B has downloadable open weights; the other is API-only.

## Snapshot

| | Step 5 Preview | Yi-34B |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 47.9 | 27.8 |
| Rank | 58 | 329 |
| Context | 1.02M | — |
| Input $/M | $1 | — |
| Output $/M | $2.70 | — |
| Weights | Proprietary | Open |

## Coding

- Step 5 Preview: 51.8 (#36)
- Yi-34B: 32.3 (#274)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Coding | 1480 | 1112 |
| LMArena WebDev | 1564 | — |
| SciCode | 58.9% | — |

## Reasoning

- Step 5 Preview: 40.0 (#57)
- Yi-34B: 21.2 (#226)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1104 |
| CritPt | 20.9% | — |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |

## Math

- Step 5 Preview: 46.1 (#72)
- Yi-34B: 21.6 (#282)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Math | 1470 | 1114 |
| ProofBench | 42% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Step 5 Preview: 41.2 (#112)
- Yi-34B: 7.5 (#309)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Expert | 1470 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |

## Multimodal

- Step 5 Preview: 41.0 (#41)
- Yi-34B: —

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Vision | 1267 | — |

## Multilingual

- Step 5 Preview: 53.8 (#54)
- Yi-34B: 29.7 (#264)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Non-English | 1432 | 1079 |
| LMArena Chinese | 1519 | 1176 |
| LMArena Russian | 1436 | 1050 |
| LMArena Spanish | 1439 | 1070 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |

## Instruction Following

- Step 5 Preview: 76.0 (#50)
- Yi-34B: 56.2 (#274)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1444 | 1091 |

## Long Context

- Step 5 Preview: 44.5 (#64)
- Yi-34B: 33.2 (#264)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1455 | 1094 |

## Writing & Preference

- Step 5 Preview: 62.8 (#71)
- Yi-34B: 34.1 (#273)

| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Text | 1442 | 1129 |
| LMArena Creative Writing | 1410 | 1108 |
| LMArena Multi-Turn | 1447 | 1113 |

## FAQ

### Is Step 5 Preview better than Yi-34B?

Step 5 Preview is the stronger model overall, scoring 47.9 to 27.8 on the Noometry Index.

### Is Step 5 Preview or Yi-34B better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 32.3 in the Noometry coding category.

### How many benchmarks do Step 5 Preview and Yi-34B share?

13 benchmarks have published results for both models. Step 5 Preview has 18 scored results on Noometry and Yi-34B has 23.