AI21 LabsOpen weightsAuto-detected

Jamba 1.7 Large

Name: Jamba 1.7 Large benchmark results
Creator: BenchLeader

Best configuration ranks #483 of 610 on the BenchLeader Index at 41.6 ±1.2.

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	default	Source
GPQA Diamond (AA)not in index	39.0%#457	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.7%#491	Artificial Analysis

Benchmark	default	Source
Terminal-Bench Hard	2.3%#304	Artificial Analysis
τ²-Bench Telecom (AA)not in index	13.4%#354	Artificial Analysis

Benchmark	default	Source
AA-Omniscience	-54.9#359	Artificial Analysis

Benchmark	default	Source
IFBench	35.2%#296	Artificial Analysis

Benchmark	default	Source
AA-LCR	19.3%#366	Artificial Analysis

Benchmark	default	Source
AA Intelligence Index	6.1#455	Artificial Analysis