Provider logo

Qwen3.8 2.4T A95B (Max)

qwen/qwen3.8-2.4t-a95b
Provider logo

Qwen3.8 2.4T A95B (Max)

qwen/qwen3.8-2.4t-a95b

This is the same underlying model as Qwen3.8 Max, exposed under its architecture-based 2.4T A95B name for easier discovery. It uses the identical routing, pricing, capabilities, and non-thinking mode.

Added Aug 26, 2026

Model weights

Context Window

991.0K

Max Output

65.5K

Input Price (Auto)

$2.00/1M

Output Price (Auto)

$6.00/1M

Cache Read (Auto)

$0.20/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

57.7

Better than 98% of models compared

Coding Index

71.9

Better than 92% of models compared

Agentic Index

57.1

Better than 96% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

93.5%

Better than 99% of models compared

HLE

Humanity's Last Exam

42.4%

Better than 95% of models compared

AA-LCR

Long context reasoning evaluation

75.3%

Better than 91% of models compared

GDPval-AA

Economically valuable tasks

60.8%

CritPt

Research-level physics reasoning

20.0%

Coding

SciCode

Python programming for scientific computing

51.6%

Better than 93% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

31.3%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

39.2%

Last updated Aug 25, 2026, 12:00 AM

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Qwen3.8 2.4T A95B (Max) with similar models from the same provider or model family.