AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#85

Qwen3.8 2.4T A95B

Qwen Release: 2026-08-12 Tested on: 2026-08-12 23:32 qwen/qwen3.8-2.4t-a95b::high
2.4T total (95B active)MoEWeights available
(high) (low)

Summary

Qwen3.8 2.4T A95B scores 7.5 on AI BENCHY and ranks #85. It has 8.8 reliability, a 77.3% pass rate, $2.755 total cost, and 134.41s average response time.

What makes Qwen3.8 2.4T A95B unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-08-12

Reported
Parameters
2.4T total (95B active)
Architecture
MoE
Availability
Weights available
License
Apache-2.0

Exact open-weight sparse checkpoint; public weights use the Qwen Apache-2.0 release license.

Parameter source Availability source

Score

7.5

Consistency

8.4

Reliability

8.8

Total Cost (Current Price)

$2.755

Total Output Tokens

512,351

Total Input Tokens

109,036

Input Price

$2.000 / 1M

Output Price

$6.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 77.3%

Flaky tests

4

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

134.41s

Response Time (max): 532.28s

Response Time (total): 2956.97s

Did not follow instructions: 2 No answer: 2 Wrong answer: 2 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#85 Qwen3.8 2.4T A95B

high
Invalid SVG
Cost
$0.000
Time
600.0s
Tokens
0 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-12 23:12 $2.000 / 1M $6.000 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Qwen3.8 2.4T A95BhighvsQwen3.5 Plus 2026-02-15mediumQwen3.8 2.4T A95BhighvsQwen3.5-27BmediumQwen3.8 2.4T A95BhighvsGPT-5.4 MinimediumQwen3.8 2.4T A95BhighvsQwen3.7 MaxnoneQwen3.8 2.4T A95BhighvsGPT-5.6 TerralowQwen3.8 2.4T A95BhighvsLongCat 2.0mediumQwen3.8 2.4T A95BhighvsGPT-5.3 ChatnoneQwen3.8 2.4T A95BhighvsGemini 3 Flash PreviewlowQwen3.8 2.4T A95BhighvsGPT-5.4 NanomediumQwen3.8 2.4T A95BhighvsGrok 4.6low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 5.9 6.3
Combined 6.9 5.9
Data parsing and extraction 10.0 10.0
Domain specific 5.6 7.2
General Intelligence 6.1 3.1
Instructions following 9.8 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models