DeepSeekDeepSeek-Coder-V2 236B
As of 6 Nov 2026, DeepSeek-Coder-V2 236B by DeepSeek is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. Released 17 Jun 2024.
Key facts (as of 6 Nov 2026)
- DeepSeek-Coder-V2 236B was released on 17 Jun 2024 (DeepSeek).
In detail. DeepSeek-Coder-V2 236B is a DeepSeek model, released 17 Jun 2024. It is not yet ranked: no independent benchmark results so far, only pricing and metadata.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Full answer
- –
- Cost per task
- –
- Tokens per task
- –
- Released
- 17 Jun 2024
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| WinoGrandenot in index | 83.7%#8 | Epoch AI Benchmarking Hub |
| ARC (AI2 Challenge)not in index | 64.3%#31 | Epoch AI Benchmarking Hub |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| GSM8Knot in index | 85.8%#12 | Epoch AI Benchmarking Hub |
More from DeepSeek
See also
Questions people ask
- Why does DeepSeek-Coder-V2 236B have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 6 Nov 2026 DeepSeek-Coder-V2 236B does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- When was DeepSeek-Coder-V2 236B released?
- DeepSeek released DeepSeek-Coder-V2 236B on 17 Jun 2024.
Data as of 6 Nov 2026. Compare with another model.
Cite as: BenchLeader, “DeepSeek-Coder-V2 236B: benchmarks, pricing, speed and rank”, data as of 6 Nov 2026, https://www.benchleader.com/models/deepseek-coder-v2-base.