# Qwen3.8 Max vs Yi-34B

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-8-max-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Qwen3.8 Max 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 Max leads 61.7 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 92.7% for Qwen3.8 Max and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.8 Max | Yi-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 56.8 | 27.8 |
| Rank | 22 | 329 |
| Context | 1M | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Proprietary | Open |

## Coding

- Qwen3.8 Max: 53.5 (#29)
- Yi-34B: 32.3 (#274)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Coding | 1502 | 1112 |
| DeepSWE | 57.5% | — |
| LMArena WebDev | 1674 | — |
| FrontierSWE | 17.8% | — |
| SciCode | 53.2% | — |

## Agentic & Tool Use

- Qwen3.8 Max: 45.4 (#14)
- Yi-34B: —

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| APEX-Agents | 63.3% | — |
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |

## Reasoning

- Qwen3.8 Max: 54.4 (#26)
- Yi-34B: 21.2 (#226)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1104 |
| Epoch Capabilities Index | 156.41 | 117.39 |
| NYT Connections (extended) | 88.3% | — |
| CritPt | 20% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- Qwen3.8 Max: 73.2 (#20)
- Yi-34B: 21.6 (#282)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Math | 1499 | 1114 |
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Qwen3.8 Max: 61.7 (#27)
- Yi-34B: 7.5 (#309)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| GPQA Diamond | 92.7% | 14.7% |
| LMArena Expert | 1507 | 1061 |
| SimpleQA Verified | 47.3% | — |
| MMLU | — | 76.3% |

## Multimodal

- Qwen3.8 Max: 37.2 (#75)
- Yi-34B: —

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |

## Multilingual

- Qwen3.8 Max: 56.7 (#18)
- Yi-34B: 29.7 (#264)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Non-English | 1472 | 1079 |
| LMArena Chinese | 1538 | 1176 |
| LMArena French | 1503 | 1081 |
| LMArena German | 1483 | 1042 |
| LMArena Japanese | 1467 | 993 |
| LMArena Korean | 1461 | 959 |
| LMArena Russian | 1481 | 1050 |
| LMArena Spanish | 1492 | 1070 |

## Instruction Following

- Qwen3.8 Max: 77.6 (#17)
- Yi-34B: 56.2 (#274)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1479 | 1091 |

## Long Context

- Qwen3.8 Max: 45.6 (#31)
- Yi-34B: 33.2 (#264)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1489 | 1094 |

## Writing & Preference

- Qwen3.8 Max: 67.1 (#30)
- Yi-34B: 34.1 (#273)

| Benchmark | Qwen3.8 Max | Yi-34B |
|---|---|---|
| LMArena Text | 1483 | 1129 |
| LMArena Creative Writing | 1479 | 1108 |
| LMArena Multi-Turn | 1489 | 1113 |

## FAQ

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

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 27.8 on the Noometry Index.

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

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 32.3 in the Noometry coding category.

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

19 benchmarks have published results for both models. Qwen3.8 Max has 39 scored results on Noometry and Yi-34B has 23.