Home/Models/Qwen-1_8B
Alibaba Qwen logo

Qwen-1_8B

by Alibaba Qwen · Released Jan 2024

Open Source
15.9
avg score
Rank #256
Compare
Better than 7% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
6 tested
Data updated today
About

Tested on 6 benchmarks with 28.7% average. Top scores: LAMBADA (58.4%), PIQA (46.6%), ARC AI2 (37.6%).

Capabilities
reasoning
4.3
#190 globally
math
21.2
#186 globally
knowledge
36.7
#190 globally
Benchmark Scores
Compare All
Tested on 6 benchmarks · Ranked across 3 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
BBH

BIG-Bench Hard. 23 challenging tasks from BIG-Bench where prior language models fell below average human performance.

4.3
GSM8K

Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.

21.2
LAMBADA

Language modeling benchmark testing ability to predict the last word of passages requiring long-range context understanding.

58.4
PIQA

Physical Intuition QA. Tests understanding of everyday physical interactions and commonsense physics.

46.6
ARC AI2

AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.

37.6
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Alibaba Qwen logoAlibaba QwenTBD
Share & Export
Tweet
Qwen-1_8B is an open-source text AI model by Alibaba Qwen, released in January 2024. It has an average benchmark score of 15.9.