BenchLeader
AllenaiAuto-detected

Olmo 3.1 32B

Best configuration ranks #410 of 610 on the BenchLeader Index at 44.6 ±7.6 (thinking reasoning effort). Last measured 2 Sept 2026.

Blended price
Output speed
First answer
Context
66k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index45
  2. Reasoning46
  3. Coding46
  4. Agents & tools34
  5. Knowledge44
  6. Instruction following65
  7. Human preference44
  8. Long context25
  9. Composite38

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.

EffortIndexRankSpeedFirst answerChat reply costCategories
thinkingbest44.6#410Agents & tools 34 · Coding 46 · Composite 38 · Human preference 44 · Instruction following 65 · Knowledge 44 · Long context 25 · Reasoning 46
default43.4#439Agents & tools 34 · Coding 51 · Composite 37 · Human preference 50 · Instruction following 42 · Knowledge 39 · Long context 25 · Reasoning 51

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.

Reasoning

BenchmarkthinkingdefaultSource
LMArena Hard Prompts1305#2321348#195LMArena
GPQA Diamond (AA)not in index59.1%#36253.9%#389Artificial Analysis
Humanity's Last Exam (AA)not in index6.3%#3265.0%#377Artificial Analysis

Coding

BenchmarkthinkingdefaultSource
LMArena Coding1340#2311382#191LMArena

Agents & tools

BenchmarkthinkingdefaultSource
Terminal-Bench Hard0.0%#3450.0%#345Artificial Analysis
τ²-Bench Telecom (AA)not in index0.0%#37521.4%#309Artificial Analysis

Knowledge

BenchmarkthinkingdefaultSource
AA-Omniscience-43.4#275-52.4#335Artificial Analysis

Instruction following

BenchmarkthinkingdefaultSource
IFBench66.0%#9939.2%#259Artificial Analysis

Human preference

BenchmarkthinkingdefaultSource
LMArena Text1286#2451330#200LMArena

Long context

BenchmarkthinkingdefaultSource
AA-LCR0.0%#4190.0%#419Artificial Analysis

Composite

BenchmarkthinkingdefaultSource
AA Intelligence Index7.1#4126.5#439Artificial Analysis

See also

Data as of 9 Sept 2026. Compare these configurations.