# DeepSeek Coder 33B vs Llama 3-8B

> Llama 3-8B has enough public results to be ranked (#338); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-33b-vs-llama-3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 1 category and Llama 3-8B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 30.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 51.1% for DeepSeek Coder 33B and 36.9% for Llama 3-8B.

## Snapshot

| | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 38.3 | 25.3 |
| Rank | — | 338 |
| Context | — | 8K |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.14 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 33B: 37.4 (#180)
- Llama 3-8B: 30.5 (#285)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 42% | 31.9% |
| BigCodeBench Complete | 51.1% | 36.9% |
| HumanEval+ | 75% | 56.7% |
| MBPP+ | 70.1% | 54.8% |
| LMArena Coding | — | 1152 |

## Reasoning

- DeepSeek Coder 33B: —
- Llama 3-8B: 13.8 (#321)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 116.33 |
| WinoGrande | 62% | 75.7% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1133 |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |

## Math

- DeepSeek Coder 33B: —
- Llama 3-8B: 8.3 (#317)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LMArena Math | — | 1151 |
| MATH Level 5 | — | 6.1% |
| GSM8K | 35.4% | — |

## Knowledge

- DeepSeek Coder 33B: —
- Llama 3-8B: 7.8 (#303)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 82.8% |
| MMLU | 39.4% | 68.8% |
| GPQA Diamond | — | 26.1% |
| LMArena Expert | — | 1113 |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |

## Multilingual

- DeepSeek Coder 33B: —
- Llama 3-8B: 31.0 (#256)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| LMArena Non-English | — | 1098 |
| LMArena Chinese | — | 1076 |
| LMArena French | — | 1158 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1003 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1172 |

## Instruction Following

- DeepSeek Coder 33B: —
- Llama 3-8B: 58.7 (#255)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | — | 1127 |

## Long Context

- DeepSeek Coder 33B: —
- Llama 3-8B: 34.2 (#246)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | — | 1128 |

## Writing & Preference

- DeepSeek Coder 33B: —
- Llama 3-8B: 37.7 (#251)

| Benchmark | DeepSeek Coder 33B | Llama 3-8B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1150 |
| LMArena Multi-Turn | — | 1152 |

## FAQ

### Is DeepSeek Coder 33B better than Llama 3-8B?

Llama 3-8B has enough public results to be ranked (#338); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 33B or Llama 3-8B better for coding?

DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 30.5 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 33B and Llama 3-8B share?

8 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Llama 3-8B has 34.