MiniMax M2.7 vs Qwen3.5-27B

Change models
IndexAll categories, out of 100.
51.2 ±4.5
51.3 ±4.3 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
85%
90% best
SpeedOutput tokens per second.
35/s
69/s best
EloLMArena rating and rank.
1405
1409 best
ReleasedMonth of release.
2026-03
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.21 best
$0.26
Output / 1MUS dollars per 1M output tokens.
$0.84 best
$2.60
1K chats2K tokens in, 500 out, each.
$0.84 best
$1.82
1K documents20K tokens in, 1K out, each.
$5.04 best
$7.80
1K agent tasks200K tokens in, 20K out, each.
$58.80 best
$104.00
ContextMaximum tokens in one request.
197K
262K best
AgenticMulti-step tasks with tools.
52.0 best
50.3
CodingCode writing and repair.
52.3
52.7 best
ReasoningLogic problems and puzzles.
49.5
50.5 best
MultimodalTasks with images and text.
—
53.9
KnowledgeFacts and expert knowledge.
50.2 best
49.0
MultilingualTasks in many languages.
—
51.6
InstructionTasks with strict prompt rules.
59.8 best
57.1
MathMath problems.
47.7
—

Benchmarks

10 shared
Only MiniMax M2.7: 43Only Qwen3.5-27B: 19
MiniMax M2.7
Qwen3.5-27B
29.6% best82 / 222
23.9%101 / 222
78.3% best63 / 217
77.7%74 / 217
0.6%132 / 214
0.9% best124 / 214
87.4% best57 / 199
85.8%71 / 199
26.8% best92 / 164
20.7%127 / 164
84.8%58 / 149
93.9% best29 / 149
75.7% best19 / 146
75.6%21 / 146
40.4% best36 / 52
39.4%39 / 52
57.0% best22 / 41
41.6%36 / 41
51.9%
58.9%