Alibaba · Released Apr 5, 2026
Qwen3.8 2.4T A95B
Alibaba's massive 2.4T parameter Mixture-of-Experts model offering frontier reasoning with permissive open weights.
OpenRating Index
57.9
0–100 composite
Reasoning Index
79.8
0–100 composite
Cost / Task
$1.09
benchmark run
Output speed
65 tok/s
blended tok/s
Time to first token
0.8s
median latency
Input price
$0.4
per 1M tokens
Output price
$1.6
per 1M tokens
Context window
256K
tokens
Strengths
Massive MoE architecture with specialized expert routing
Superior multilingual translation and domain knowledge
Extensive tool-use evaluation benchmark scores
How we rate Qwen3.8 2.4T A95B
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
57.9
Reasoning Index
79.8
Token Pricing
Input per 1M tokens
$0.4
Output per 1M tokens
$1.6
Cost of 1M input + 1M output
$2
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($1.09 total).
Related models
Compare Qwen3.8 2.4T A95B with the models it is most often measured against.