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 13B
LLaMA 13B is an open-weight model from Meta. It ranks #418 of 351 on the LMArena text leaderboard with a rating of 834.
LMArena text834+0 in 30 days
Rank#418/351
95% interval818–849
Votes2.4K
- Developer
- Meta
- Released
- May 8, 2023
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · Non-commercial
- Inputs
- —
- Reasoning
- —
- Tool use
- —
LatestLLaMA 13B 834
The rating LMArena published at each update since May 8, 2023. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 834 | 418 / 351 | 2.4K |
| CodingLMArena | 683 | 413 / 346 | 304 |
| MathLMArena | 838 | 404 / 339 | 252 |
| Creative writingLMArena | 794 | 416 / 349 | 431 |
| Instruction followingLMArena | 781 | 418 / 351 | 584 |
| Hard promptsLMArena | 728 | 418 / 351 | 430 |
| Multi-turnLMArena | 753 | 415 / 349 | 247 |
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 13B
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 13B?
LLaMA 13B is made by Meta, founded 2013 (FAIR) and based in Menlo Park.
How does LLaMA 13B rank?
#418 of 351 on LMArena’s text leaderboard, rated 834 (95% interval 818–849) from 2,391 votes, as of Oct 22, 2026.
Is LLaMA 13B open source?
LLaMA 13B has open weights under the Non-commercial license.