
Olmo 3 32B Think
Olmo 3 32B Think is an open-weight model from Ai2. It ranks #250 of 351 on the LMArena text leaderboard with a rating of 1300.
LMArena text1300−0 in 30 days
Rank#250/351
95% interval1291–1308
Votes5.8K
- Developer
- Ai2
- Released
- Dec 5, 2025
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · Apache 2.0
- Inputs
- —
- Reasoning
- —
- Tool use
- —
LatestOlmo 3 32B Think 1300
The rating LMArena published at each update since Dec 5, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1300 | 250 / 351 | 5.8K |
| CodingLMArena | 1319 | 245 / 346 | 1K |
| MathLMArena | 1317 | 229 / 339 | 329 |
| Creative writingLMArena | 1256 | 265 / 349 | 863 |
| Instruction followingLMArena | 1274 | 253 / 351 | 1.5K |
| Hard promptsLMArena | 1302 | 247 / 351 | 3K |
| Multi-turnLMArena | 1290 | 255 / 349 | 771 |
| Long queriesLMArena | 1295 | 253 / 330 | 1.4K |
| ExpertLMArena | 1274 | 244 / 305 | 313 |
| Legal and governmentIndustries | 1289 | 261 / 325 | 414 |
| Medicine and healthcareIndustries | 1315 | 236 / 325 | 323 |
| Business and financeIndustries | 1290 | 242 / 344 | 1.1K |
| ChineseLanguages | 1300 | 247 / 328 | 488 |
| GermanLanguages | 1290 | 202 / 261 | 136 |
| FrenchLanguages | 1291 | 221 / 252 | 124 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Olmo 3 32B Think
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 Olmo 3 32B Think?
Olmo 3 32B Think is made by Ai2, founded 2014 and based in Seattle.
How does Olmo 3 32B Think rank?
#250 of 351 on LMArena’s text leaderboard, rated 1300 (95% interval 1291–1308) from 5,825 votes, as of Oct 22, 2026.
Is Olmo 3 32B Think open source?
Olmo 3 32B Think has open weights under the Apache 2.0 license.
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
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