
DeepSeek-Coder-V2
DeepSeek-Coder-V2 is an open-weight model from DeepSeek. It ranks #325 of 351 on the LMArena text leaderboard with a rating of 1191.
- Developer
- DeepSeek
- Released
- Jun 21, 2024
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · DeepSeek License
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Jun 21, 2024. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1191 | 325 / 351 | 15.1K |
| CodingLMArena | 1251 | 294 / 346 | 2.7K |
| MathLMArena | 1241 | 287 / 339 | 1.9K |
| Creative writingLMArena | 1120 | 348 / 349 | 2.3K |
| Instruction followingLMArena | 1180 | 321 / 351 | 5.6K |
| Hard promptsLMArena | 1207 | 309 / 351 | 4.4K |
| Multi-turnLMArena | 1177 | 323 / 349 | 2.7K |
| Long queriesLMArena | 1219 | 308 / 330 | 1.8K |
| ExpertLMArena | 1181 | 298 / 305 | 769 |
| Legal and governmentIndustries | 1163 | 332 / 325 | 888 |
| Medicine and healthcareIndustries | 1133 | 329 / 325 | 847 |
| Business and financeIndustries | 1155 | 327 / 344 | 1.8K |
| ChineseLanguages | 1201 | 310 / 328 | 1.7K |
| SpanishLanguages | 1153 | 273 / 249 | 245 |
| GermanLanguages | 1164 | 269 / 261 | 516 |
| FrenchLanguages | 1185 | 262 / 252 | 207 |
| JapaneseLanguages | 1126 | 244 / 236 | 345 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare DeepSeek-Coder-V2
DeepSeek
A research lab known for strong open-weight reasoning and coding models trained at low cost. Founded 2023, based in Hangzhou. deepseek.com
Questions
Who makes DeepSeek-Coder-V2?
DeepSeek-Coder-V2 is made by DeepSeek, founded 2023 and based in Hangzhou.
How does DeepSeek-Coder-V2 rank?
#325 of 351 on LMArena’s text leaderboard, rated 1191 (95% interval 1185–1198) from 15,147 votes, as of Oct 22, 2026.
Is DeepSeek-Coder-V2 open source?
DeepSeek-Coder-V2 has open weights under the DeepSeek License license.
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview