Jamba 1.5 Large
AI21 LabsOpen WeightJamba Open Model License
Description
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
398.0B
Context Length
—
Modalities
text
Capability Radar
24
general
15
coding
29
reasoning
26
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 388 | 15.0 | AA |
| General Ranking | 383 | 28.0 | AA |
| Math Reasoning | 258 | 32.0 | AA |
| Science | 398 | 24.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
36.9%SR
Communication
Wild Bench
48.5%SR
Creativity
Arena Hard
65.4%SR
Finance
MMLU
81.2%SR
TruthfulQA
58.3%SR
MMLU-Pro
53.5%SR
General
ARC-C
93.0%SR
Math
GSM8k
87.0%SR
AA Evaluation Indices
Intelligence Index10.7
Math 5000.6
Mmlu Pro0.6
Gpqa0.4
Scicode0.2
Livecodebench0.1
Aime0.0
Hle0.0
LLM Stats Category Scores
Writing70
Creativity70
Language70
Math70
Reasoning70
Finance60
General60
Healthcare60
Legal60
Communication50
Biology40
Chemistry40
Physics40
Pricing
Input Price$2 / 1M tokens
Output Price$8 / 1M tokens
Blended Price (3:1)$3.5 / 1M tokens
Speed
Tokens/sec0.0 tokens/s
Time to First Token0.00s
Time to Answer0.00s
Available Providers
(LS internal units)No provider data available