Jamba Reasoning 3B

by AI21 Labs

Released · 93 days after Jamba 1.7 Mini

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index3.8
Math Index10.7
Reasoning & knowledge
MMLU-Pro
58%
GPQA Diamond
33%
Humanity's Last Exam
4%
Long-context reasoning
8%
Coding
LiveCodeBench
21%
SciCode
6%
Agentic & tool use
Terminal-Bench Hard
1%
τ²-Bench Telecom
16%
Math & instruction following
AIME 2025
11%
IFBench
52%

Available routes

No routes currently available — Jamba Reasoning 3B isn't routed through the Opper gateway right now. It's tracked here for its release history.

Contact us about this model →

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Jamba Reasoning 3B — release date & benchmarks | Opper AI