Claude Opus 5.5 vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
78.3 ±2.4 best
72.0 ±8.0
GapIndex points below the top.
Top
−6.3 · no clear gap
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
87/s best
40/s
EloLMArena rating and rank.
1514
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$4.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$20.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
—
1K chats2K tokens in, 500 out, each.
$18.00
$5.25 best
1K documents20K tokens in, 1K out, each.
$100.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$1,200.00
$390.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
73.7
75.2 best
CodingCode writing and repair.
81.1 best
67.0
ReasoningLogic problems and puzzles.
80.6
—
MultimodalTasks with images and text.
75.3 best
72.1
KnowledgeFacts and expert knowledge.
79.3 best
70.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
59.4
—
MathMath problems.
77.3
—

Benchmarks

16 shared
Only Claude Opus 5.5: 144Only Qwen4 Max: 3
Claude Opus 5.5
Qwen4 Max
65.5% best3 / 167
43.7%42 / 167
90.3% best6 / 125
86.7%14 / 125
50.5% best8 / 92
41.3%31 / 92
44.5% best7 / 84
40.4%12 / 84
65.2% best1 / 63
48.5%14 / 63
DeepSWEAgentic
74.2%11 / 61
75.7% best5 / 61
17.5 best4 / 56
8.415 / 56
64.4% best2 / 54
51.7%8 / 54
9.2%24 / 37
21.3% best7 / 37
56.3% best4 / 26
46.3%15 / 26
69.5%8 / 24
72.6% best6 / 24
26.2%9 / 23
26.2%9 / 23
59.6% best4 / 23
48.5%13 / 23
91.2% best2 / 21
31.5%12 / 21
64.4% best5 / 11
54.2%7 / 11
65.6%
60.0%