What are Jamba Reasoning 3B's benchmark scores?

As of 25 Oct 2026, Jamba Reasoning 3B (thinking effort) scores 41.9 ±6.5 on the BenchLeader Index, strongest in instruction following (54) and weakest in long context (27). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does Jamba Reasoning 3B rank?

Jamba Reasoning 3B (thinking effort) is #614 of 785 ranked configurations on 25 Oct 2026. 354 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Jamba Reasoning 3B released?

AI21 Labs released Jamba Reasoning 3B on 8 Oct 2025.

AI21 LabsOpen weightsReasoning modelCompare with another model

Jamba Reasoning 3B

Jamba Reasoning 3B is an AI21 Labs open-weights reasoning model, released 8 Oct 2025. Its best configuration (thinking reasoning effort) ranks #614 of 785 on the BenchLeader Index at 41.9 ±6.5, in the lower half. The ± is the point: 354 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (54) and lowest in long context (27). Last measured 8 Oct 2025.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 262k
Full answer: –
Cost per run: –
Released: 8 Oct 2025

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index42
Reasoning41
Agents & tools34
Knowledge36
Instruction following54
Long context27
Composite36

How its index has moved

9 Sept 2026 to 18 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. 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

Benchmark	thinking	Source
GPQA Diamond (AA)not in index	33.3%#503	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.8%#571	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Agents & tools

Benchmark	thinking	Source
Terminal-Bench Hard	0.8%#349	Artificial Analysis
τ²-Bench Telecom (AA)not in index	15.8%#359	Artificial Analysis

Knowledge

Benchmark	thinking	Source
AA-Omniscience	-57.7#448	Artificial Analysis
AA-Omniscience: accuracynot in index	6.7%#532	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	31.0%#218	Artificial Analysis

Instruction following

Benchmark	thinking	Source
IFBench	52.5%#161	Artificial Analysis

Long context

Benchmark	thinking	Source
AA-LCR	6.3%#482	Artificial Analysis

Composite

Benchmark	thinking	Source
AA Intelligence Index v4.3.2	5.7#566	Artificial Analysis

New this month

Questions people ask

What are Jamba Reasoning 3B's benchmark scores?: As of 25 Oct 2026, Jamba Reasoning 3B (thinking effort) scores 41.9 ±6.5 on the BenchLeader Index, strongest in instruction following (54) and weakest in long context (27). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Jamba Reasoning 3B rank?: Jamba Reasoning 3B (thinking effort) is #614 of 785 ranked configurations on 25 Oct 2026. 354 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Jamba Reasoning 3B released?: AI21 Labs released Jamba Reasoning 3B on 8 Oct 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Jamba Reasoning 3B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/jamba-3b.