
DeepSeek-V2.5
DeepSeek-V2.5 is an open-weight model from DeepSeek. It ranks #254 of 351 on the LMArena text leaderboard with a rating of 1294.
- Developer
- DeepSeek
- Released
- Sep 15, 2024
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · DeepSeek
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Sep 15, 2024. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1294 | 254 / 351 | 6.8K |
| CodingLMArena | 1309 | 252 / 346 | 1.1K |
| MathLMArena | 1288 | 247 / 339 | 1K |
| Creative writingLMArena | 1285 | 239 / 349 | 1.1K |
| Instruction followingLMArena | 1280 | 247 / 351 | 3K |
| Hard promptsLMArena | 1289 | 254 / 351 | 1.8K |
| Multi-turnLMArena | 1297 | 250 / 349 | 1.2K |
| Long queriesLMArena | 1300 | 247 / 330 | 1K |
| ExpertLMArena | 1266 | 247 / 305 | 441 |
| Legal and governmentIndustries | 1282 | 269 / 325 | 1.5K |
| Medicine and healthcareIndustries | 1292 | 251 / 325 | 291 |
| Business and financeIndustries | 1259 | 265 / 344 | 715 |
| ChineseLanguages | 1318 | 240 / 328 | 446 |
| SpanishLanguages | 1248 | 246 / 249 | 293 |
| GermanLanguages | 1258 | 225 / 261 | 140 |
| FrenchLanguages | 1289 | 222 / 252 | 222 |
| JapaneseLanguages | 1228 | 197 / 236 | 161 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (DeepSeek-V2.5 (1210), DeepSeek-V2.5).
Compare DeepSeek-V2.5
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-V2.5?
DeepSeek-V2.5 is made by DeepSeek, founded 2023 and based in Hangzhou.
How does DeepSeek-V2.5 rank?
#254 of 351 on LMArena’s text leaderboard, rated 1294 (95% interval 1286–1302) from 6,795 votes, as of Oct 22, 2026.
Is DeepSeek-V2.5 open source?
DeepSeek-V2.5 has open weights under the DeepSeek 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