# Qwen3.8 27B vs Yi-34B

> Qwen3.8 27B is the stronger model overall, scoring 45.3 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-8-27b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Qwen3.8 27B 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 Qwen3.8 27B leads 40.9 to 7.5.

## Snapshot

| | Qwen3.8 27B | Yi-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 45.3 | 27.4 |
| Rank | 64 | 325 |
| Context | 262K | — |
| Input $/M | $0.99 | — |
| Output $/M | $1.49 | — |
| Weights | Open | Open |

## Coding

- Qwen3.8 27B: 50.3 (#42)
- Yi-34B: 31.8 (#269)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Coding | 1487 | 1112 |
| LMArena WebDev | 1592 | — |
| SciCode | 46.6% | — |

## Reasoning

- Qwen3.8 27B: 31.5 (#71)
- Yi-34B: 20.3 (#222)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1459 | 1104 |
| Epoch Capabilities Index | 149.38 | 117.28 |
| NYT Connections (extended) | 54.5% | — |
| CritPt | 5.4% | — |
| DTBench | 88% | — |
| LMCA | 41.4% | — |
| Surface Evolver Bench | 45% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- Qwen3.8 27B: 35.7 (#139)
- Yi-34B: 19.8 (#277)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Math | 1453 | 1114 |
| ProofBench | 16% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Qwen3.8 27B: 40.9 (#105)
- Yi-34B: 7.5 (#304)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Expert | 1482 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |

## Multimodal

- Qwen3.8 27B: 40.5 (#36)
- Yi-34B: —

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Vision | 1270 | — |

## Multilingual

- Qwen3.8 27B: 54.0 (#54)
- Yi-34B: 29.9 (#259)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1431 | 1079 |
| LMArena Chinese | 1504 | 1175 |
| LMArena French | 1468 | 1080 |
| LMArena German | 1435 | 1042 |
| LMArena Japanese | 1392 | 993 |
| LMArena Korean | 1389 | 959 |
| LMArena Russian | 1421 | 1050 |
| LMArena Spanish | 1444 | 1070 |

## Instruction Following

- Qwen3.8 27B: 75.8 (#54)
- Yi-34B: 56.4 (#269)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1436 | 1091 |

## Long Context

- Qwen3.8 27B: 44.3 (#66)
- Yi-34B: 33.2 (#259)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1448 | 1094 |

## Writing & Preference

- Qwen3.8 27B: 65.9 (#41)
- Yi-34B: 34.3 (#268)

| Benchmark | Qwen3.8 27B | Yi-34B |
|---|---|---|
| LMArena Text | 1441 | 1129 |
| LMArena Creative Writing | 1382 | 1108 |
| LMArena Multi-Turn | 1443 | 1113 |
| EQ-Bench Creative Writing | 1671 | — |

## FAQ

### Is Qwen3.8 27B better than Yi-34B?

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 27.4 on the Noometry Index.

### Is Qwen3.8 27B or Yi-34B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 31.8 in the Noometry coding category.

### How many benchmarks do Qwen3.8 27B and Yi-34B share?

18 benchmarks have published results for both models. Qwen3.8 27B has 28 scored results on Noometry and Yi-34B has 23.