Kimi K3.1 Pro vs Qwen4 Max

Change models
Kimi K3.1 ProMoonshot AISmartest open
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
75.5 ±4.7 best
72.0 ±8.0
GapIndex points below the top.
Top
−3.5 · no clear gap
CoverageIndex weight that has results.
80% best
65%
SpeedOutput tokens per second.
30/s
40/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
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.
$5.42
—
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.
1.05M best
1M
AgenticMulti-step tasks with tools.
76.3 best
75.2
CodingCode writing and repair.
71.9 best
67.0
ReasoningLogic problems and puzzles.
78.7
—
MultimodalTasks with images and text.
71.7
72.1 best
KnowledgeFacts and expert knowledge.
70.7
70.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
—

Benchmarks

8 shared
Only Kimi K3.1 Pro: 56Only Qwen4 Max: 11
Kimi K3.1 Pro
Qwen4 Max
48.9% best24 / 167
43.7%42 / 167
70.0% best2 / 79
51.7%22 / 79
DeepSWEAgentic
75.5%6 / 61
75.7% best5 / 61
51.1%9 / 54
51.7% best8 / 54
38.8%24 / 26
46.3% best15 / 26
73.3% best5 / 24
72.6%6 / 24
31.4% best2 / 23
26.2%9 / 23
67.2% best1 / 23
48.5%13 / 23