← Back to Model Leaderboard

Qwen3.8 Max

Official information

Release date: Aug 2, 2026
Official model ID: qwen3.8-max

Vendor source: Qwen3.8 Max
Identity verified: —

API pricing

Verification: Verified
Verified at: Oct 27, 2026, 06:10:02 GMT+8
Value benchmark tier: qwen3-8-max-international-0

Input / output per million tokens
Tier / region	Input / output · per MTok	Context pricing tier	Billing	Validity	Source
qwen3-8-max-international-0 international	$2 / $6	0–1,000,000 tokens	Standard online · Cache miss All day	Current	Official rates Oct 27, 2026, 06:10:02 GMT+8

Rankings by category

Overall

#6High 0.82

82.3

Overall — Source breakdown
Source	Percentile	Raw score	Config folding
LiveBench	79.3	79.5	Single config
LMArena	85.3	1483.6	Single config

Cross-source percentile spread 5.9

Coding

#9High 0.80

78.1

Coding — Source breakdown
Source	Percentile	Raw score	Config folding
DeepSWE	64.6	57.5	Single config
LiveBench	85.9	67.9	Single config
LMArenatext-coding	79.4	1502.6	Single config
· webdev	88.3	1672.2	Single config

Cross-source percentile spread 21.3

Agent

#12High 0.90

63.1

Agent — Source breakdown
Source	Percentile	Raw score	Config folding
Agents' Last Exam	76.8	52.5	Single config
DeepSWE	64.6	57.5	Single config
LMArena	47.9	0.0	Single config

Cross-source percentile spread 28.9

Reasoning

#9High 0.92

76.5

Reasoning — Source breakdown
Source	Percentile	Raw score	Config folding
Epoch AI	80.2	0.9	Single config
LiveBench	64.1	89.8	Single config
LMArenatext-math	85.3	1501.1	Single config
· text-hard	85.3	1496.6	Single config

Cross-source percentile spread 21.2

Value

#4High 0.82

62.7

Aliases & configurations

qwen3-8
qwen3-8-max

Methodology & data sources