# Step 3 vs Yi-Lightning

> Step 3 is the stronger model overall, scoring 39.9 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/step-3-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Step 3 scores higher in 8 categories and Yi-Lightning in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3 leads 39.5 to 27.0.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Step 3 | Yi-Lightning |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 39.9 | 36.5 |
| Rank | 145 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Step 3: 39.5 (#144)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1367 | 1313 |
| Aider Polyglot | — | 12.9% |

## Reasoning

- Step 3: 27.6 (#102)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1302 |
| Kagi LLM Benchmark | 62.3% | — |

## Math

- Step 3: 34.9 (#148)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1366 | 1300 |

## Knowledge

- Step 3: 36.2 (#161)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1333 | 1286 |

## Multimodal

- Step 3: 34.9 (#81)
- Yi-Lightning: —

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1176 | — |

## Multilingual

- Step 3: 46.5 (#154)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1327 | 1269 |
| LMArena Chinese | 1396 | 1320 |
| LMArena German | 1371 | 1267 |
| LMArena Korean | 1271 | 1192 |
| LMArena Russian | 1331 | 1255 |
| LMArena Spanish | 1372 | 1315 |
| LMArena French | — | 1304 |
| LMArena Japanese | — | 1228 |

## Instruction Following

- Step 3: 70.6 (#159)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1332 | 1278 |

## Long Context

- Step 3: 40.3 (#152)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1326 | 1297 |

## Writing & Preference

- Step 3: 54.5 (#146)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Step 3 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1351 | 1302 |
| LMArena Creative Writing | 1322 | 1280 |
| LMArena Multi-Turn | 1340 | 1311 |

## FAQ

### Is Step 3 better than Yi-Lightning?

Step 3 is the stronger model overall, scoring 39.9 to 36.5 on the Noometry Index.

### Is Step 3 or Yi-Lightning better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 27.0 in the Noometry coding category.

### How many benchmarks do Step 3 and Yi-Lightning share?

15 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Yi-Lightning has 18.