Jamba 1.5 Mini
AI21 LabsOpen WeightJamba Open Model License
Description
Part of the Jamba 1.5 family, a state-of-the-art hybrid SSM-Transformer instruction following foundation model offering superior long context handling, speed, and quality.
Release Date
2024-08-22
Parameters
52.0B
Context Length
—
Modalities
text
Capability Radar
15
general
6
coding
17
reasoning
22
science
14
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 608 | 7.0 | AA |
| General Ranking | 626 | 15.0 | AA |
| Science | 615 | 16.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
69.7%SR
TruthfulQA
54.1%SR
Arena Hard
46.1%SR
Wild Bench
42.4%SR
Language
MMLU-Pro
42.5%SR
Math
GSM8k
75.8%SR
Reasoning
ARC-C
85.7%SR
GPQANYU + Cohere + Anthropic (2023)
32.3%SR
AA Evaluation Indices
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))37.1
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))35.7
Gpqa(NYU + Cohere + Anthropic (2023))30.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))6.2
Intelligence Index(Artificial Analysis)5.2
Hle(Center for AI Safety + Scale AI (2025))5.1
Aime(MAA (Mathematical Association of America))1.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Language60
Legal60
Math60
Reasoning60
Finance60
General60
Healthcare60
Chat50
Creativity50
Writing50
Communication40
Physics30
Biology30
Chemistry30
Pricing
Input Price$0.2 / 1M tokens
Output Price$0.4 / 1M tokens
Blended Price (3:1)$0.25 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1AI21 LabsPRIMARY
$0.2
$0.4
Compare pricing across different API providers for this model.