# Step 3 vs Yi-1.5-34B

> Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/step-3-vs-yi-1-5-34b
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Step 3 scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 14.8.

## Snapshot

| | Step 3 | Yi-1.5-34B |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 40.5 | 30.6 |
| Rank | 149 | 289 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Step 3: 40.1 (#147)
- Yi-1.5-34B: 32.4 (#272)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1367 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |

## Reasoning

- Step 3: 28.4 (#105)
- Yi-1.5-34B: 22.5 (#191)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1160 |
| Kagi LLM Benchmark | 62.3% | — |

## Math

- Step 3: 37.6 (#148)
- Yi-1.5-34B: 27.5 (#249)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1366 | 1182 |
| MATH Level 5 | — | 25.5% |

## Knowledge

- Step 3: 36.8 (#164)
- Yi-1.5-34B: 14.8 (#295)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1333 | 1144 |
| GPQA Diamond | — | 32% |

## Multimodal

- Step 3: 35.5 (#86)
- Yi-1.5-34B: —

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Vision | 1177 | — |

## Multilingual

- Step 3: 46.3 (#159)
- Yi-1.5-34B: 32.3 (#256)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1327 | 1121 |
| LMArena Chinese | 1397 | 1213 |
| LMArena German | 1371 | 1111 |
| LMArena Korean | 1269 | 1005 |
| LMArena Russian | 1331 | 1091 |
| LMArena Spanish | 1371 | 1121 |
| LMArena French | — | 1156 |
| LMArena Japanese | — | 1021 |

## Instruction Following

- Step 3: 70.4 (#164)
- Yi-1.5-34B: 59.2 (#257)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1332 | 1139 |

## Long Context

- Step 3: 40.3 (#157)
- Yi-1.5-34B: 34.6 (#248)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1326 | 1143 |

## Writing & Preference

- Step 3: 54.3 (#151)
- Yi-1.5-34B: 37.4 (#257)

| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1350 | 1173 |
| LMArena Creative Writing | 1321 | 1135 |
| LMArena Multi-Turn | 1341 | 1153 |

## FAQ

### Is Step 3 better than Yi-1.5-34B?

Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.

### Is Step 3 or Yi-1.5-34B better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 32.4 in the Noometry coding category.

### How many benchmarks do Step 3 and Yi-1.5-34B share?

15 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Yi-1.5-34B has 21.