# DeepSeek LLM 67B vs StarCoder 2 15B

> DeepSeek LLM 67B has enough public results to be ranked (#347); StarCoder 2 15B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-starcoder-2-15b
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek LLM 67B scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.6 to 31.9.

## Snapshot

| | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 24.9 | 38.1 |
| Rank | 347 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- StarCoder 2 15B: 36.6

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| LMArena Coding | 1096 | — |
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 110.5 | 105 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| WinoGrande | — | 64.3% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 57.7% |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- StarCoder 2 15B: —

| Benchmark | DeepSeek LLM 67B | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |

## FAQ

### Is DeepSeek LLM 67B better than StarCoder 2 15B?

DeepSeek LLM 67B has enough public results to be ranked (#347); StarCoder 2 15B does not yet, so treat this comparison as directional.

### Is DeepSeek LLM 67B or StarCoder 2 15B better for coding?

StarCoder 2 15B scores higher on coding benchmarks: 36.6 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and StarCoder 2 15B share?

1 benchmark has published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and StarCoder 2 15B has 7.