Gemini 4 Argon
Claude Opus 5.5
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
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
Llama 3.1 405B Instruct
Llama 3.1 405B Instruct is an open-weight model from Meta. It ranks #267 of 351 on the LMArena text leaderboard with a rating of 1284.
- Developer
- Meta
- Released
- Jul 30, 2024
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · Llama 3.1 Community
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Jul 30, 2024. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1284 | 267 / 351 | 41.4K |
| CodingLMArena | 1291 | 265 / 346 | 6.2K |
| MathLMArena | 1281 | 254 / 339 | 8.5K |
| Creative writingLMArena | 1262 | 261 / 349 | 8.9K |
| Instruction followingLMArena | 1259 | 267 / 351 | 23.6K |
| Hard promptsLMArena | 1269 | 271 / 351 | 10.7K |
| Multi-turnLMArena | 1297 | 249 / 349 | 6.8K |
| Long queriesLMArena | 1265 | 277 / 330 | 5.5K |
| ExpertLMArena | 1243 | 264 / 305 | 3.1K |
| Legal and governmentIndustries | 1303 | 249 / 325 | 3.4K |
| Medicine and healthcareIndustries | 1286 | 256 / 325 | 1.9K |
| Business and financeIndustries | 1247 | 276 / 344 | 6.7K |
| ChineseLanguages | 1242 | 278 / 328 | 3.1K |
| SpanishLanguages | 1260 | 240 / 249 | 348 |
| GermanLanguages | 1252 | 230 / 261 | 894 |
| FrenchLanguages | 1279 | 231 / 252 | 364 |
| JapaneseLanguages | 1208 | 206 / 236 | 846 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (Llama 3.1 405B Instruct (BF16), Llama 3.1 405B Instruct (FP8)).
Compare Llama 3.1 405B Instruct
Meta
Meta’s AI research publishes the Llama family, among the most downloaded open-weight models. Founded 2013 (FAIR), based in Menlo Park. ai.meta.com
Questions
Who makes Llama 3.1 405B Instruct?
Llama 3.1 405B Instruct is made by Meta, founded 2013 (FAIR) and based in Menlo Park.
How does Llama 3.1 405B Instruct rank?
#267 of 351 on LMArena’s text leaderboard, rated 1284 (95% interval 1280–1287) from 41,375 votes, as of Oct 22, 2026.
Is Llama 3.1 405B Instruct open source?
Llama 3.1 405B Instruct has open weights under the Llama 3.1 Community license.