Claude Opus 5 vs Qwen4 Max

Change models
Claude Opus 5Anthropic
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
73.0 ±1.9 best
72.0 ±8.0
GapIndex points below the top.
Top
−1.0 · no clear gap
CoverageIndex weight that has results.
100% best
65%
SpeedOutput tokens per second.
70/s best
40/s
EloLMArena rating and rank.
1502
—
ReleasedMonth of release.
2026-07
2026-11
Input / 1MUS dollars per 1M input tokens.
$5.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
—
1K chats2K tokens in, 500 out, each.
$22.50
$5.25 best
1K documents20K tokens in, 1K out, each.
$125.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$390.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.1
75.2 best
CodingCode writing and repair.
74.2 best
67.0
ReasoningLogic problems and puzzles.
75.0
—
MultimodalTasks with images and text.
66.8
72.1 best
KnowledgeFacts and expert knowledge.
72.9 best
70.7
MultilingualTasks in many languages.
63.2
—
InstructionTasks with strict prompt rules.
55.5
—
MathMath problems.
74.4
—

Benchmarks

14 shared
Only Claude Opus 5: 137Only Qwen4 Max: 5
Claude Opus 5
Qwen4 Max
60.9% best7 / 167
43.7%42 / 167
88.4% best11 / 125
86.7%14 / 125
55.3% best2 / 92
41.3%31 / 92
47.1% best6 / 84
40.4%12 / 84
64.7% best4 / 79
51.7%22 / 79
53.5% best11 / 63
48.5%14 / 63
DeepSWEAgentic
68.8%25 / 61
75.7% best5 / 61
2.720 / 56
8.4 best15 / 56
56.3% best6 / 54
51.7%8 / 54
53.8% best5 / 26
46.3%15 / 26
93.0% best1 / 21
31.5%12 / 21
29.6%11 / 11
54.2% best7 / 11
47.5%
48.5%
59.8%
60.0%