# DeepSeek V4.1 Flash vs Yi-34B

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash leads 57.9 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 89.8% for DeepSeek V4.1 Flash and 14.7% for Yi-34B.

## Snapshot

| | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 52.8 | 27.8 |
| Rank | 38 | 329 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.9 (#32)
- Yi-34B: 32.3 (#274)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Coding | 1506 | 1112 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| ALE-Bench | 1,092 | — |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: 31.2 (#69)
- Yi-34B: —

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |

## Reasoning

- DeepSeek V4.1 Flash: 50.2 (#36)
- Yi-34B: 21.2 (#226)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1104 |
| Epoch Capabilities Index | 154.9 | 117.39 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- DeepSeek V4.1 Flash: 66.7 (#25)
- Yi-34B: 21.6 (#282)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Math | 1477 | 1114 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- DeepSeek V4.1 Flash: 57.9 (#38)
- Yi-34B: 7.5 (#309)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| GPQA Diamond | 89.8% | 14.7% |
| LMArena Expert | 1506 | 1061 |
| MMLU | — | 76.3% |

## Multimodal

- DeepSeek V4.1 Flash: 39.1 (#61)
- Yi-34B: —

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- DeepSeek V4.1 Flash: 55.0 (#35)
- Yi-34B: 29.7 (#264)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Non-English | 1448 | 1079 |
| LMArena Chinese | 1497 | 1176 |
| LMArena French | 1452 | 1081 |
| LMArena German | 1484 | 1042 |
| LMArena Japanese | 1412 | 993 |
| LMArena Korean | 1452 | 959 |
| LMArena Russian | 1471 | 1050 |
| LMArena Spanish | 1459 | 1070 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.3 (#26)
- Yi-34B: 56.2 (#274)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1474 | 1091 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#47)
- Yi-34B: 33.2 (#264)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1475 | 1094 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.4 (#48)
- Yi-34B: 34.1 (#273)

| Benchmark | DeepSeek V4.1 Flash | Yi-34B |
|---|---|---|
| LMArena Text | 1462 | 1129 |
| LMArena Creative Writing | 1435 | 1108 |
| LMArena Multi-Turn | 1457 | 1113 |
| EQ-Bench Creative Writing | 1540 | — |

## FAQ

### Is DeepSeek V4.1 Flash better than Yi-34B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 27.8 on the Noometry Index.

### Is DeepSeek V4.1 Flash or Yi-34B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 32.3 in the Noometry coding category.

### How many benchmarks do DeepSeek V4.1 Flash and Yi-34B share?

19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Yi-34B has 23.