Back
FR

AI21 Labs

Jamba 1.7 Large

Intelligence
6.1
Rank 657 of 782 measured models
Context window
256K
Rank 583 of 1325 measured models

Jamba 1.7 Large scores 6.1 on the Artificial Analysis Intelligence Index, ranking 657th of 782 measured models. The closest models on this index are DeepHermes 3 - Mistral 24B Preview (Non-reasoning) (6.1), Qwen3.5 0.8B (6.1), and DeepSeek-Coder-V2 (6.0).

Artificial Analysis Indices
Intelligence6.1
Rank 657 of 782 measured models
Math2.3
Rank 259 of 270 measured models
Standard Benchmarks
MMLU Pro57.7%
Rank 277 of 349 measured models
GPQA Diamond39.0%
Rank 535 of 621 measured models
HLE3.7%
Rank 629 of 682 measured models
LiveCodeBench18.1%
Rank 276 of 343 measured models
MATH-50060.0%
Rank 160 of 202 measured models
AIME 20245.7%
Rank 152 of 194 measured models
AIME 20252.3%
Rank 259 of 270 measured models
IFBench35.2%
Rank 330 of 451 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy