AI21 LabsOpen weightsReasoning modelAuto-detected

Jamba Reasoning 3B

Name: Jamba Reasoning 3B benchmark results
Creator: BenchLeader

Best configuration ranks #463 of 610 on the BenchLeader Index at 42.3 ±7.3 (thinking reasoning effort).

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
GPQA Diamond (AA)not in index	33.3%#474	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.8%#486	Artificial Analysis

Benchmark	thinking	Source
Terminal-Bench Hard	0.8%#332	Artificial Analysis
τ²-Bench Telecom (AA)not in index	15.8%#344	Artificial Analysis

Benchmark	thinking	Source
AA-Omniscience	-57.7#372	Artificial Analysis

Benchmark	thinking	Source
IFBench	52.5%#158	Artificial Analysis

Benchmark	thinking	Source
AA-LCR	6.3%#409	Artificial Analysis

Benchmark	thinking	Source
AA Intelligence Index	5.7#478	Artificial Analysis