# DeepSeek LLM 67B vs Qwen3-Coder 480B-A35B Instruct

> Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Coder 480B-A35B Instruct leads 36.4 to 7.1.

## Snapshot

| | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 37.7 |
| Rank | 341 | 186 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Coding | 1096 | 1413 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1108 | 1364 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1337 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1073 | 1345 |
| LMArena Chinese | 1132 | 1356 |
| LMArena French | — | 1394 |
| LMArena German | — | 1324 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1307 |
| LMArena Russian | — | 1367 |
| LMArena Spanish | — | 1360 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1079 | 1356 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1092 | 1379 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

| Benchmark | DeepSeek LLM 67B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1105 | 1356 |
| LMArena Creative Writing | 1067 | 1333 |
| LMArena Multi-Turn | 1082 | 1365 |

## FAQ

### Is DeepSeek LLM 67B better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Qwen3-Coder 480B-A35B Instruct share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.