MiMo-V2-Pro vs Qwen3.6-27B

Change models
IndexAll categories, out of 100.
51.5 ±7.6
51.5 ±2.4
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
75%
100% best
SpeedOutput tokens per second.
—
44/s
EloLMArena rating and rank.
1436
—
ReleasedMonth of release.
2026-03
2026-04
Input / 1MUS dollars per 1M input tokens.
—
$0.32
Output / 1MUS dollars per 1M output tokens.
—
$3.20
1K chats2K tokens in, 500 out, each.
—
$2.24
1K documents20K tokens in, 1K out, each.
—
$9.60
1K agent tasks200K tokens in, 20K out, each.
—
$128.00
ContextMaximum tokens in one request.
1M best
262K
AgenticMulti-step tasks with tools.
53.0
55.9 best
CodingCode writing and repair.
58.2 best
52.2
ReasoningLogic problems and puzzles.
45.3
48.6 best
MultimodalTasks with images and text.
—
52.6
KnowledgeFacts and expert knowledge.
52.0 best
48.0
MultilingualTasks in many languages.
—
60.7
InstructionTasks with strict prompt rules.
52.6 best
43.3
MathMath problems.
—
50.3

Benchmarks

10 shared
Only MiMo-V2-Pro: 1Only Qwen3.6-27B: 54
MiMo-V2-Pro
Qwen3.6-27B
30.4% best76 / 216
23.1%100 / 216
68.3%117 / 211
77.3% best76 / 211
0.3%132 / 207
1.1% best113 / 207
87.0% best57 / 193
84.2%80 / 193
26.6% best94 / 170
19.6%136 / 170
95.0% best21 / 143
94.2%24 / 143
68.8% best46 / 140
67.6%50 / 140
78.0% best30 / 114
77.2%37 / 114
36.7%44 / 51
54.8% best17 / 51
Claw-EvalAgentic
57.8%30 / 42
72.4% best8 / 42