AI BENCHY
Advertise here
#36

Qwen3.8 Max (0902)

Qwen Release: 2026-09-07 Tested on: 2026-09-07 16:06 qwen/qwen3.8-max-0902::medium
2.4T total (~100B active)MoEClosedEstimated
(high) (medium) (low)

Summary

Qwen3.8 Max (0902) scores 8.8 on AI BENCHY and ranks #36. It has 10.0 reliability, a 83.3% pass rate, $0.677 total cost, and 26.01s average response time.

Model facts

Researched on 2026-09-07

Estimated
Parameters
2.4T total (~100B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. OpenRouter reports 2400B total and MoE for this snapshot. Active count is undisclosed; 100B is a low-confidence estimate carried from the preceding Qwen3.8 Max catalog record, not a reported snapshot specification. QwenCloud identifies this as an API snapshot.

Parameter source 1 Parameter source 2 Availability source

Score

8.8

Consistency

9.3

Reliability

10.0

Total Cost (Current Price)

$0.677

Total Output Tokens

80,678

Total Input Tokens

96,323

Input Price

$2.000 / 1M

Output Price

$6.000 / 1M

Tests Correct

Wrong Tests: 5

Attempt pass rate: 83.3%

Flaky tests

2

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

Response Time (avg)

26.01s

Response Time (max): 168.09s

Response Time (total): 572.19s

Wrong answer: 5

Hamster playing table tennis

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

#36 Qwen3.8 Max (0902)

medium
Cost
$0.036
Time
108.3s
Tokens
5,980 tok

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 Max (0902)mediumvsGemini 3.5 FlashlowQwen3.8 Max (0902)mediumvsMuse Spark 1.3mediumQwen3.8 Max (0902)mediumvsSeed 2.1 TurbohighQwen3.8 Max (0902)mediumvsGemini 3.5 Flash LitehighQwen3.8 Max (0902)mediumvsMuse Spark 1.3highQwen3.8 Max (0902)mediumvsClaude Opus 4.8mediumQwen3.8 Max (0902)mediumvsGPT-5.3-CodexmediumQwen3.8 Max (0902)mediumvsClaude Opus 5lowQwen3.8 Max (0902)mediumvsQwen3.8 Max (0902)highQwen3.8 Max (0902)mediumvsGemini 3.6 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 8.4 7.4
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models