GPT-6 Astra vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
77.7 ±1.9 best
72.0 ±8.0
GapIndex points below the top.
Top
−5.7 · no clear gap
CoverageIndex weight that has results.
100% best
65%
SpeedOutput tokens per second.
33/s
40/s best
EloLMArena rating and rank.
1440
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$5.25 best
1K documents20K tokens in, 1K out, each.
$250.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$390.00 best
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
74.2
75.2 best
CodingCode writing and repair.
76.4 best
67.0
ReasoningLogic problems and puzzles.
83.8
—
MultimodalTasks with images and text.
70.8
72.1 best
KnowledgeFacts and expert knowledge.
78.3 best
70.7
MultilingualTasks in many languages.
73.3
—
InstructionTasks with strict prompt rules.
79.0
—
MathMath problems.
77.6
—

Benchmarks

13 shared
Only GPT-6 Astra: 127Only Qwen4 Max: 6
GPT-6 Astra
Qwen4 Max
61.6% best6 / 167
43.7%42 / 167
89.6% best8 / 125
86.7%14 / 125
39.4%39 / 92
41.3% best31 / 92
20.7%54 / 84
40.4% best12 / 84
59.6% best5 / 63
48.5%14 / 63
DeepSWEAgentic
74.1%12 / 61
75.7% best5 / 61
13.5 best7 / 56
8.415 / 56
7.1%27 / 37
21.3% best7 / 37
51.2% best8 / 26
46.3%15 / 26
68.5%9 / 24
72.6% best6 / 24
31.0% best3 / 23
26.2%9 / 23
59.1% best6 / 23
48.5%13 / 23
64.7%
60.0%