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 Tulu 3 70B
Llama 3.1 Tulu 3 70B is an open-weight model from Ai2. It ranks #294 of 351 on the LMArena text leaderboard with a rating of 1256.
LMArena text1256+0 in 30 days
Rank#294/351
95% interval1245–1266
Votes2.8K
- Developer
- Ai2
- Released
- Jan 5, 2025
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · Llama 3.1
- Inputs
- —
- Reasoning
- —
- Tool use
- —
LatestLlama 3.1 Tulu 3 70B 1256
The rating LMArena published at each update since Jan 5, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1256 | 294 / 351 | 2.8K |
| CodingLMArena | 1235 | 300 / 346 | 450 |
| MathLMArena | 1242 | 286 / 339 | 397 |
| Creative writingLMArena | 1231 | 293 / 349 | 441 |
| Instruction followingLMArena | 1233 | 294 / 351 | 1.2K |
| Hard promptsLMArena | 1220 | 299 / 351 | 779 |
| Multi-turnLMArena | 1252 | 292 / 349 | 537 |
| Long queriesLMArena | 1224 | 306 / 330 | 463 |
| Business and financeIndustries | 1226 | 288 / 344 | 288 |
| ChineseLanguages | 1249 | 272 / 328 | 224 |
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 Tulu 3 70B
Ai2
The Allen Institute for AI builds OLMo, fully open models with open data and training code. Founded 2014, based in Seattle. allenai.org
Questions
Who makes Llama 3.1 Tulu 3 70B?
Llama 3.1 Tulu 3 70B is made by Ai2, founded 2014 and based in Seattle.
How does Llama 3.1 Tulu 3 70B rank?
#294 of 351 on LMArena’s text leaderboard, rated 1256 (95% interval 1245–1266) from 2,846 votes, as of Oct 22, 2026.
Is Llama 3.1 Tulu 3 70B open source?
Llama 3.1 Tulu 3 70B has open weights under the Llama 3.1 license.