Olmo-3.1-32B-Think
Ai2- Arena score
- 1271
- Among open models
- #98of 148
- Among all on Arena
- #286
- Votes
- 8,244
Measured on Olmo 3.1 32B Think, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1344#82#2363.3K
- Hard prompts, English1328#83#2451.7K
- Applied math1311#80#237376
- Math1305#81#238473
- Software & IT1301#90#2632.7K
- Expert1294#82#239550
- Coding1290#92#2701.5K
- Science1290#91#2691.4K
- Spanish1289#74#225199
- Legal & government1287#90#265616
- Hard prompts1272#92#2704.3K
- Long prompts1271#93#2782K
- German1262#72#225165
- French1262#75#241208
- Medicine & health1261#95#270587
- Business & finance1254#94#2741.5K
- Multi-turn1252#99#2951.2K
- Writing & literature1251#95#2911.9K
- Instructions1246#96#2862.2K
- Chinese1241#94#282721
- Media & sports1237#94#2821.6K
- Creative writing1227#98#2971.3K
- Non-English1209#104#3065K
- Russian1193#109#3181.1K
- Polish1191#77#237335
- Excluding ties1190#98#2865.9K
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/allenai_Olmo-3.1-32B-Think-GGUF7 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Olmo-3.1-32B-Think-4bit8 builds
Most downloaded
- allenai_Olmo-3.1-32B-Think-GGUFbartowski · Quantization4K downloads
- Olmo-3.1-32B-Think-GGUFunsloth · Quantization1.7K downloads
- Olmo-3.1-32B-Think-i1-GGUFmradermacher · Quantization742 downloads
- Olmo-3.1-32B-Think-4bitmlx-community · Quantization587 downloads
- Olmo-3.1-32B-Think-8bitmlx-community · Quantization469 downloads
BenchClub runs
Not runnable yet
Runs open once a Olmo-3.1-32B-Think build is registered.
More from Ai2
See more
Molmo2-8B47.6K8.7B

Olmo-3.1-32B-Instruct21.3K32.2B

Olmo-3-32B-Think11.8K32.2B

Llama-3.1-Tulu-3-8B6K8.0B
Other 20–40B models
See more
Qwen3.8-27BQwen6.9M27.8B

gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B