DeepSeek, open weights
DeepSeek-V2 (MoE-236B, May 2024)
DeepSeek-V2 (MoE-236B, May 2024) by DeepSeek has 10 published benchmark results on Noometry, not yet enough to be ranked.
Last verified
Specifications
- Noometry rank
- Unranked
- Index score
- Not ranked
- Evidence
- Sparse 10 results
- Provider
DeepSeek
- Released
- May 7, 2024
- 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 40.4
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.4 | #139 | 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 | 48.9% | #5 of 64, top 8% | 2024-06-28 | BigCodeBench | 2024-06-28 |
| BigCodeBench Complete | 59.4% | #6 of 66, top 10% | 2024-06-28 | BigCodeBench | 2024-06-28 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| BIG-Bench Hard | 78.8% | #7 of 27, top 26% | Epoch AI | ||
| Epoch Capabilities Index | 124.77 | #158 of 213, top 75% | Epoch AI | 2024-05-07 | |
| HellaSwag | 87.1% | #6 of 29, top 21% | Epoch AI | ||
| PIQA | 83.9% | #7 of 27, top 26% | Epoch AI | ||
| WinoGrande | 86.3% | #6 of 43, top 14% | Epoch AI |
Knowledge
Compare DeepSeek-V2 (MoE-236B, May 2024)
- DeepSeek-V2 (MoE-236B, May 2024) vs GPT-6 Astra
- DeepSeek-V2 (MoE-236B, May 2024) vs Claude Fable 5.1
- DeepSeek-V2 (MoE-236B, May 2024) vs Claude Opus 5.5
- DeepSeek-V2 (MoE-236B, May 2024) vs Claude Opus 5
- DeepSeek-V2 (MoE-236B, May 2024) vs Claude Fable 5
- DeepSeek-V2 (MoE-236B, May 2024) vs GPT-6.1 Sol
- DeepSeek-V2 (MoE-236B, May 2024) vs Gemini 3.8 Flash
- DeepSeek-V2 (MoE-236B, May 2024) vs Kimi K3
- DeepSeek-V2 (MoE-236B, May 2024) vs Grok 4.6
- DeepSeek-V2 (MoE-236B, May 2024) vs Qwen3.8 Max
- DeepSeek-V2 (MoE-236B, May 2024) vs GLM-5.3
- DeepSeek-V2 (MoE-236B, May 2024) vs Muse Spark 1.3
- DeepSeek-V2 (MoE-236B, May 2024) vs MiMo-V2.6-Pro
Other DeepSeek models
Frequently asked questions
How good is DeepSeek-V2 (MoE-236B, May 2024)?
DeepSeek-V2 (MoE-236B, May 2024) by DeepSeek has 10 published benchmark results on Noometry, not yet enough to be ranked.
Is DeepSeek-V2 (MoE-236B, May 2024) open source?
Yes. DeepSeek-V2 (MoE-236B, May 2024)'s weights are downloadable; check the license for commercial terms.