GPT-5.5 vs Qwen4 Max

Change models
GPT-5.5OpenAI
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
68.6 ±2.4
72.0 ±8.0 best
GapIndex points below the top.
−3.4 · no clear gap
Top
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
52/s best
40/s
EloLMArena rating and rank.
1466
—
ReleasedMonth of release.
2026-04
2026-11
Input / 1MUS dollars per 1M input tokens.
$5.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$30.00
$4.50 best
Batch output / 1MBatch price per 1M output tokens.
$15.00
—
1K chats2K tokens in, 500 out, each.
$25.00
$5.25 best
1K documents20K tokens in, 1K out, each.
$130.00
$34.50 best
1K agent tasks200K tokens in, 20K out, each.
$1,600.00
$390.00 best
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
65.4
75.2 best
CodingCode writing and repair.
64.6
67.0 best
ReasoningLogic problems and puzzles.
73.6
—
MultimodalTasks with images and text.
66.5
72.1 best
KnowledgeFacts and expert knowledge.
70.1
70.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.6
—
MathMath problems.
74.3
—

Benchmarks

9 shared
Only GPT-5.5: 106Only Qwen4 Max: 10
GPT-5.5
Qwen4 Max
58.0% best10 / 167
43.7%42 / 167
69.8%52 / 125
86.7% best14 / 125
40.4%37 / 92
41.3% best31 / 92
21.8%51 / 84
40.4% best12 / 84
52.2% best20 / 79
51.7%22 / 79
41.4%27 / 54
51.7% best8 / 54
37.7%7 / 31
59.1% best1 / 31
50.0% best10 / 26
46.3%15 / 26
46.6%
48.5%