Olmo-3.1-32B-Instruct
Ai2- Arena score
- 1311
- Among open models
- #82of 148
- Among all on Arena
- #247
- Votes
- 11,731
Measured on Olmo 3.1 32B Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1354#77#2274.5K
- Hard prompts, English1353#76#2272.4K
- Software & IT1349#78#2323.9K
- Applied math1348#73#220433
- Coding1347#78#2332.4K
- Spanish1337#67#203370
- Legal & government1332#75#229882
- French1329#67#206323
- Hard prompts1322#79#2386.3K
- Business & finance1317#79#2302.1K
- Science1317#83#2471.9K
- Long prompts1312#78#2402.9K
- Multi-turn1310#79#2442.1K
- Math1307#80#237686
- Expert1306#78#232752
- Chinese1304#82#246875
- Instructions1299#79#2413.2K
- Medicine & health1287#88#257776
- German1282#68#213245
- Writing & literature1276#85#2642.6K
- Non-English1276#83#2537.2K
- Media & sports1270#81#2482.1K
- Russian1269#85#2641.7K
- Creative writing1266#85#2601.7K
- Excluding ties1250#82#2478.4K
- Polish1221#75#233383
- Korean1205#68#220180
About as strong, smaller
Compare
gemma-3n-E4B-itGoogle13067.8B
granite-4.2-8bIBM Granite13198.8B
gemma-3-12b-itGoogle133412.2B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/allenai_Olmo-3.1-32B-Instruct-GGUF8 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Olmo-3.1-32B-Instruct-MLX-4bit5 builds
Most downloaded
- allenai_Olmo-3.1-32B-Instruct-GGUFbartowski · Quantization7.6K downloads
- Olmo-3.1-32B-Instruct-GGUFunsloth · Quantization1.9K downloads
- Olmo-3.1-32B-Instruct-GGUFlmstudio-community · Quantization1.5K downloads
- Olmo-3.1-32B-Instruct-MLX-4bitlmstudio-community · Quantization793 downloads
- Olmo-3.1-32B-Instruct-4bitmlx-community · Quantization565 downloads
BenchClub runs
Not runnable yet
Runs open once a Olmo-3.1-32B-Instruct build is registered.
More from Ai2
See more
Molmo2-8B47.6K8.7B

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

Olmo-3.1-32B-Think7.7K32.2B

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