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 70B Instruct
Llama 3.1 70B Instruct is an open-weight model from Meta, released Jul 23, 2024. It ranks #292 of 351 on the LMArena text leaderboard with a rating of 1261. It costs $0.40 per million input tokens and $0.40 per million output tokens, with a 128K-token context window.
- Developer
- Meta
- Released
- Jul 23, 2024
- Context window
- 128K
- Price in / out, per 1M tokens
- $0.40 / $0.40
- Weights
- Open · Llama 3.1 Community
- Inputs
- Text
- Reasoning
- No
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 89.5K
- Hugging Face likes
- 1K
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 | 1261 | 292 / 351 | 55.2K |
| CodingLMArena | 1260 | 291 / 346 | 9.4K |
| MathLMArena | 1252 | 279 / 339 | 7.7K |
| Creative writingLMArena | 1232 | 292 / 349 | 8.3K |
| Instruction followingLMArena | 1231 | 295 / 351 | 21.9K |
| Hard promptsLMArena | 1241 | 295 / 351 | 15K |
| Multi-turnLMArena | 1256 | 288 / 349 | 10.4K |
| Long queriesLMArena | 1241 | 295 / 330 | 7.6K |
| ExpertLMArena | 1209 | 286 / 305 | 2.9K |
| Legal and governmentIndustries | 1284 | 267 / 325 | 3.2K |
| Medicine and healthcareIndustries | 1257 | 274 / 325 | 2.8K |
| Business and financeIndustries | 1235 | 283 / 344 | 6.4K |
| ChineseLanguages | 1215 | 301 / 328 | 4.8K |
| SpanishLanguages | 1253 | 244 / 249 | 606 |
| GermanLanguages | 1222 | 247 / 261 | 1.4K |
| FrenchLanguages | 1262 | 242 / 252 | 501 |
| JapaneseLanguages | 1132 | 241 / 236 | 1.4K |
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 3.1 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 3.1 70B Instruct?
Llama 3.1 70B Instruct is made by Meta, founded 2013 (FAIR) and based in Menlo Park.
How much does Llama 3.1 70B Instruct cost?
$0.40 per million input tokens and $0.40 per million output tokens, at its provider’s list price.
What is Llama 3.1 70B Instruct’s context window?
128K tokens (131,072).
How does Llama 3.1 70B Instruct rank?
#292 of 351 on LMArena’s text leaderboard, rated 1261 (95% interval 1257–1265) from 55,240 votes, as of Oct 22, 2026.
Is Llama 3.1 70B Instruct open source?
Llama 3.1 70B Instruct has open weights under the Llama 3.1 Community license, downloadable from Hugging Face (meta-llama/Meta-Llama-3.1-70B-Instruct).