# Qwen3 14B vs Yi-Lightning

> Yi-Lightning is the stronger model overall, scoring 37.1 to 35.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-14b-vs-yi-lightning
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Qwen3 14B leads 37.3 to 27.4.
- Qwen3 14B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3 14B | Yi-Lightning |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 35.5 | 37.1 |
| Rank | 225 | 209 |
| Context | 131K | — |
| Input $/M | $0.35 | — |
| Output $/M | $1.40 | — |
| Weights | Open | Proprietary |

## Coding

- Qwen3 14B: 37.3 (#195)
- Yi-Lightning: 27.4 (#320)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| SciCode | 31.6% | — |
| LMArena Coding | — | 1312 |

## Agentic & Tool Use

- Qwen3 14B: 29.6 (#83)
- Yi-Lightning: —

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | — |

## Reasoning

- Qwen3 14B: 18.5 (#280)
- Yi-Lightning: 25.9 (#139)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | — |
| CritPt | 0% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1302 |
| DTBench | 64% | — |
| LMCA | 18.2% | — |
| Epoch Capabilities Index | 138.23 | — |

## Math

- Qwen3 14B: 38.6 (#133)
- Yi-Lightning: 36.2 (#172)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LMArena Math | — | 1300 |

## Knowledge

- Qwen3 14B: 39.3 (#134)
- Yi-Lightning: 35.4 (#185)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| GPQA Diamond | 63.8% | — |
| Vectara Hallucination Rate | 5.4% | — |
| LMArena Expert | — | 1286 |

## Multilingual

- Qwen3 14B: —
- Yi-Lightning: 42.2 (#196)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |

## Instruction Following

- Qwen3 14B: —
- Yi-Lightning: 67.4 (#196)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | — | 1278 |

## Long Context

- Qwen3 14B: 38.1 (#204)
- Yi-Lightning: 39.4 (#181)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
| LMArena Longer Query | — | 1297 |

## Writing & Preference

- Qwen3 14B: —
- Yi-Lightning: 50.2 (#184)

| Benchmark | Qwen3 14B | Yi-Lightning |
|---|---|---|
| LMArena Text | — | 1302 |
| LMArena Creative Writing | — | 1280 |
| LMArena Multi-Turn | — | 1311 |

## FAQ

### Is Qwen3 14B better than Yi-Lightning?

Yi-Lightning is the stronger model overall, scoring 37.1 to 35.5 on the Noometry Index.

### Is Qwen3 14B or Yi-Lightning better for coding?

Qwen3 14B scores higher on coding benchmarks: 37.3 versus 27.4 in the Noometry coding category.

### How many benchmarks do Qwen3 14B and Yi-Lightning share?

0 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Yi-Lightning has 18.