MiMo-V2.6-Pro vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
69.7 ±4.7
72.0 ±8.0 best
GapIndex points below the top.
−2.3 · no clear gap
Top
CoverageIndex weight that has results.
80% best
65%
SpeedOutput tokens per second.
33/s
40/s best
EloLMArena rating and rank.
1492
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.435 best
$1.50
Output / 1MUS dollars per 1M output tokens.
$0.87 best
$4.50
1K chats2K tokens in, 500 out, each.
$1.31 best
$5.25
1K documents20K tokens in, 1K out, each.
$9.57 best
$34.50
1K agent tasks200K tokens in, 20K out, each.
$104.40 best
$390.00
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
71.4
75.2 best
CodingCode writing and repair.
66.5
67.0 best
ReasoningLogic problems and puzzles.
67.7
—
MultimodalTasks with images and text.
—
72.1
KnowledgeFacts and expert knowledge.
64.0
70.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
70.9
—

Benchmarks

13 shared
Only MiMo-V2.6-Pro: 46Only Qwen4 Max: 6
MiMo-V2.6-Pro
Qwen4 Max
34.8%69 / 167
43.7% best42 / 167
85.2%18 / 125
86.7% best14 / 125
47.1% best17 / 92
41.3%31 / 92
32.4%24 / 84
40.4% best12 / 84
31.3%26 / 63
48.5% best14 / 63
DeepSWEAgentic
71.9%19 / 61
75.7% best5 / 61
0.627 / 56
8.4 best15 / 56
13.8%14 / 37
21.3% best7 / 37
37.5%26 / 26
46.3% best15 / 26
58.6%16 / 24
72.6% best6 / 24
19.2%19 / 23
26.2% best9 / 23
34.8%16 / 23
48.5% best13 / 23
26.5%16 / 21
31.5% best12 / 21