ModelBeat
Models/Qwen3.8 2.4T A95B
All models
Q

Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is Qwen’s AI model, released Aug 12, 2026. It costs $2/M input and $6/M output tokens, and handles a 1M-token context window. Its strongest use case is reasoning & knowledge, where it ranks in the 90th percentile of the models Model Beat tracks.

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total.

Context
1M
Input
$2 / 1M
Output
$6 / 1M
Released
Aug 12, 2026
Modalities
texttext
Strongest atReasoning & Knowledge top 10%Coding top 22%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen3.8 2.4T A95B lands among all models tracked on Model Beat.

84.0
Intelligence Index
Artificial Analysis
84th percentile of tracked models
78.0
Coding Index
Artificial Analysis
78th percentile of tracked models

Reasoning

2 evals
GPQA Diamond93.5%

Graduate-level scientific reasoning

Humanity's Last Exam42.4%

Frontier of human expert knowledge

Coding

1 evals
SciCode51.6%

Scientific research coding

Changelog

4
  • Qwen3.8 2.4T A95B: context window changed from 1,010,000 to 1,048,576 tokenscontext · Aug 14, 2026
  • Qwen3.8 2.4T A95B: context window changed from 1,000,000 to 1,010,000 tokenscontext · Aug 14, 2026
  • Qwen3.8 2.4T A95B: context window changed from 262,144 to 1,000,000 tokenscontext · Aug 13, 2026
  • Qwen3.8 2.4T A95B (Qwen) added to the tracker: $2/$6 per 1M, 262K context.tracked · Aug 12, 2026

Compare Qwen3.8 2.4T A95B with

Frequently asked questions

What is Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total.

Who created Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B is an AI model developed by Qwen, part of the Qwen family, released Aug 12, 2026.

How much does Qwen3.8 2.4T A95B cost?

Qwen3.8 2.4T A95B's list price from Qwen is $2 per million input tokens and $6 per million output tokens.

What is Qwen3.8 2.4T A95B's context window?

Qwen3.8 2.4T A95B supports a context window of up to 1M tokens.

How does Qwen3.8 2.4T A95B perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen3.8 2.4T A95B scores 93.5% on GPQA Diamond, 42.4% on Humanity's Last Exam, 51.6% on SciCode.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 20, 2026.