AllenaiAuto-detected

Olmo 3 32B

Name: Olmo 3 32B benchmark results
Creator: BenchLeader

Best configuration ranks #438 of 610 on the BenchLeader Index at 43.4 ±5.9 (thinking reasoning effort). Last measured 2 Sept 2026.

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Benchmark	thinking	Source
LMArena Hard Prompts	1327#213	LMArena
GPQA Diamond (AA)not in index	61.0%#351	Artificial Analysis
Humanity's Last Exam (AA)not in index	6.4%#317	Artificial Analysis

Benchmark	thinking	Source
LMArena Coding	1364#206	LMArena

Benchmark	thinking	Source
Terminal-Bench Hard	1.5%#321	Artificial Analysis
τ²-Bench Telecom (AA)not in index	0.0%#375	Artificial Analysis

Benchmark	thinking	Source
AA-Omniscience	-58.1#374	Artificial Analysis

Benchmark	thinking	Source
IFBench	49.1%#178	Artificial Analysis

Benchmark	thinking	Source
LMArena Text	1307#226	LMArena

Benchmark	thinking	Source
AA-LCR	0.0%#419	Artificial Analysis

Benchmark	thinking	Source
AA Intelligence Index	6.5#442	Artificial Analysis