DeepSeek, open weights
DeepSeek Coder 6.7B
DeepSeek Coder 6.7B by DeepSeek has 9 published benchmark results on Noometry, not yet enough to be ranked.
Last verified
Specifications
- Noometry rank
- Unranked
- Index score
- Not ranked
- Evidence
- Sparse 9 results
- Provider
DeepSeek- Released
- November 2, 2023
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- —
- Max output
- —
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
Category scores
Each category score combines every public result we have in that category.
- Coding 35.8
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 35.8 | #219 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| BigCodeBench Instruct | 35.5% | #44 of 64, top 69% | BigCodeBench | 2023-10-28 | |
| BigCodeBench Complete | 43.8% | #45 of 66, top 69% | BigCodeBench | 2023-10-28 | |
| BigCodeBench Complete | 41.8% | BigCodeBench | 2023-10-28 | ||
| HumanEval+ | 39.6% | EvalPlus | |||
| HumanEval+ | 71.3% | #19 of 45, top 43% | EvalPlus | ||
| MBPP+ | 58.7% | EvalPlus | |||
| MBPP+ | 65.6% | #19 of 38, top 50% | EvalPlus |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Epoch Capabilities Index | 89.62 | #211 of 213, top 100% | Epoch AI | 2023-11-02 | |
| WinoGrande | 57.6% | #39 of 43, top 91% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GSM8K | 21.3% | #33 of 38, top 87% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC (AI2) Challenge | 36.4% | #37 of 39, top 95% | Epoch AI | ||
| MMLU | 36.4% | #78 of 81, top 97% | Epoch AI |
Compare DeepSeek Coder 6.7B
- DeepSeek Coder 6.7B vs GPT-6 Astra
- DeepSeek Coder 6.7B vs Claude Fable 5.1
- DeepSeek Coder 6.7B vs Claude Opus 5.5
- DeepSeek Coder 6.7B vs Claude Opus 5
- DeepSeek Coder 6.7B vs Claude Fable 5
- DeepSeek Coder 6.7B vs GPT-6.1 Sol
- DeepSeek Coder 6.7B vs Gemini 3.8 Flash
- DeepSeek Coder 6.7B vs Kimi K3
- DeepSeek Coder 6.7B vs Grok 4.6
- DeepSeek Coder 6.7B vs Qwen3.8 Max
- DeepSeek Coder 6.7B vs GLM-5.3
- DeepSeek Coder 6.7B vs Muse Spark 1.3
- DeepSeek Coder 6.7B vs MiMo-V2.6-Pro
Other DeepSeek models
Frequently asked questions
How good is DeepSeek Coder 6.7B?
DeepSeek Coder 6.7B by DeepSeek has 9 published benchmark results on Noometry, not yet enough to be ranked.
Is DeepSeek Coder 6.7B open source?
Yes. DeepSeek Coder 6.7B's weights are downloadable; check the license for commercial terms.