
Llama 3 70B Instruct
Llama 3 70B Instruct is an open-weight model from Meta. It ranks #312 of 351 on the LMArena text leaderboard with a rating of 1221.
- Developer
- Meta
- Released
- Apr 18, 2024
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · Llama 3 Community
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Apr 18, 2024. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1221 | 312 / 351 | 156.9K |
| CodingLMArena | 1206 | 315 / 346 | 28.1K |
| MathLMArena | 1218 | 300 / 339 | 20.9K |
| Creative writingLMArena | 1210 | 302 / 349 | 22.8K |
| Instruction followingLMArena | 1194 | 315 / 351 | 56.6K |
| Hard promptsLMArena | 1195 | 316 / 351 | 46K |
| Multi-turnLMArena | 1223 | 302 / 349 | 21.4K |
| Long queriesLMArena | 1174 | 329 / 330 | 17.5K |
| ExpertLMArena | 1149 | 311 / 305 | 8K |
| Legal and governmentIndustries | 1228 | 305 / 325 | 8.3K |
| Medicine and healthcareIndustries | 1214 | 293 / 325 | 8.3K |
| Business and financeIndustries | 1172 | 322 / 344 | 16.6K |
| ChineseLanguages | 1114 | 341 / 328 | 15.9K |
| SpanishLanguages | 1241 | 252 / 249 | 2.7K |
| GermanLanguages | 1169 | 268 / 261 | 5K |
| FrenchLanguages | 1232 | 252 / 252 | 2.5K |
| JapaneseLanguages | 1017 | 266 / 236 | 3.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Llama 3 70B 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 70B Instruct?
Llama 3 70B Instruct is made by Meta, founded 2013 (FAIR) and based in Menlo Park.
How does Llama 3 70B Instruct rank?
#312 of 351 on LMArena’s text leaderboard, rated 1221 (95% interval 1217–1224) from 156,876 votes, as of Oct 22, 2026.
Is Llama 3 70B Instruct open source?
Llama 3 70B Instruct has open weights under the Llama 3 Community license.
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