# DeepSeek LLM 67B vs Qwen3-4B

> Qwen3-4B is the stronger model overall, scoring 31.5 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-qwen3-4b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen3-4B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 52.2% for Qwen3-4B.

## Snapshot

| | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 31.5 |
| Rank | 341 | 261 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Qwen3-4B: —

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| LMArena Coding | 1096 | — |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Qwen3-4B: 27.3 (#94)

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Qwen3-4B: 18.5 (#264)

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 0% | 4% |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.54 | — |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Qwen3-4B: 28.5 (#228)

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Qwen3-4B: 33.0 (#198)

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 24.6% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Qwen3-4B: —

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Qwen3-4B: —

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Qwen3-4B: —

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Qwen3-4B: —

| Benchmark | DeepSeek LLM 67B | Qwen3-4B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |

## FAQ

### Is DeepSeek LLM 67B better than Qwen3-4B?

Qwen3-4B is the stronger model overall, scoring 31.5 to 24.8 on the Noometry Index.

### How many benchmarks do DeepSeek LLM 67B and Qwen3-4B share?

3 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3-4B has 6.