MiMo-V2.5-Pro vs MiniMax M3

Change models
MiniMax M3MiniMax
IndexAll categories, out of 100.
55.7 ±4.6 best
55.2 ±2.9
GapIndex points below the top.
Top
−0.5 · no clear gap
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
17/s
22/s best
EloLMArena rating and rank.
1464 best
1427
ReleasedMonth of release.
2026-04
2026-06
Input / 1MUS dollars per 1M input tokens.
$0.48
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$1.80
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
—
$0.88
1K chats2K tokens in, 500 out, each.
$1.86
$1.20 best
1K documents20K tokens in, 1K out, each.
$11.40
$7.20 best
1K agent tasks200K tokens in, 20K out, each.
$132.00
$84.00 best
ContextMaximum tokens in one request.
262K
1.05M best
AgenticMulti-step tasks with tools.
57.4 best
56.9
CodingCode writing and repair.
56.6
57.1 best
ReasoningLogic problems and puzzles.
52.6 best
50.0
MultimodalTasks with images and text.
—
56.0
KnowledgeFacts and expert knowledge.
51.1
60.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
62.6 best
54.2
MathMath problems.
54.5 best
41.4

Benchmarks

31 shared
Only MiMo-V2.5-Pro: 8Only MiniMax M3: 53
MiMo-V2.5-Pro
MiniMax M3
35.7%59 / 216
39.0% best52 / 216
79.7%45 / 211
83.0% best18 / 211
4.0% best90 / 207
3.7%91 / 207
86.6%60 / 193
92.9% best13 / 193
22.4%120 / 170
44.9% best42 / 170
77.1%111 / 149
85.4% best21 / 149
TaxEval v2Finance
73.8% best46 / 143
72.7%58 / 143
94.2% best24 / 143
88.9%43 / 143
81.4%62 / 142
82.2% best53 / 142
79.9%5 / 140
82.9% best1 / 140
82.6%59 / 135
92.7% best14 / 135
MMLU ProKnowledge
84.6% best60 / 135
84.2%64 / 135
31.0%61 / 132
37.1% best48 / 132
CorpFin v2Finance
61.4%52 / 131
68.1% best11 / 131
34.1%86 / 130
47.6% best79 / 130
50.6% best49 / 113
47.1%65 / 113
MedScribeHealthcare
83.7%44 / 111
87.3% best19 / 111
MedCodeHealthcare
32.5%89 / 108
46.3% best37 / 108
15.9%78 / 98
29.8% best63 / 98
11.5%73 / 89
20.6% best59 / 89