Claude Sonnet 5.5 vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
76.5 ±2.6 best
72.0 ±8.0
GapIndex points below the top.
Top
−4.5 · no clear gap
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
104/s best
40/s
EloLMArena rating and rank.
1469
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$5.25 best
1K documents20K tokens in, 1K out, each.
$50.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$390.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
77.1 best
75.2
CodingCode writing and repair.
80.1 best
67.0
ReasoningLogic problems and puzzles.
77.9
—
MultimodalTasks with images and text.
72.9 best
72.1
KnowledgeFacts and expert knowledge.
68.9
70.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
41.6
—
MathMath problems.
75.7
—

Benchmarks

16 shared
Only Claude Sonnet 5.5: 114Only Qwen4 Max: 3
Claude Sonnet 5.5
Qwen4 Max
51.5% best17 / 167
43.7%42 / 167
92.4% best2 / 125
86.7%14 / 125
48.1% best13 / 92
41.3%31 / 92
42.0% best11 / 84
40.4%12 / 84
64.1% best3 / 63
48.5%14 / 63
DeepSWEAgentic
71.0%22 / 61
75.7% best5 / 61
13.7 best6 / 56
8.415 / 56
56.9% best5 / 54
51.7%8 / 54
10.4%22 / 37
21.3% best7 / 37
57.5% best2 / 26
46.3%15 / 26
71.8%7 / 24
72.6% best6 / 24
25.8%12 / 23
26.2% best9 / 23
63.6% best3 / 23
48.5%13 / 23
79.7% best6 / 21
31.5%12 / 21
61.6% best6 / 11
54.2%7 / 11
69.2%
60.0%