Inkling vs MiMo-V2.5

Change models
InklingThinking Machines Lab
MiMo-V2.5Xiaomi
IndexAll categories, out of 100.
54.8 ±2.9
54.8 ±6.8
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95% best
75%
SpeedOutput tokens per second.
85/s best
4/s
EloLMArena rating and rank.
1444 best
1428
ReleasedMonth of release.
2026-07
2026-04
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.40 best
Output / 1MUS dollars per 1M output tokens.
$4.05
$2.00 best
1K chats2K tokens in, 500 out, each.
$4.03
$1.80 best
1K documents20K tokens in, 1K out, each.
$24.05
$10.00 best
1K agent tasks200K tokens in, 20K out, each.
$281.00
$120.00 best
ContextMaximum tokens in one request.
524K
1M best
AgenticMulti-step tasks with tools.
51.2
56.5 best
CodingCode writing and repair.
54.1
55.5 best
ReasoningLogic problems and puzzles.
56.1
—
MultimodalTasks with images and text.
55.0
57.2 best
KnowledgeFacts and expert knowledge.
57.1 best
50.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
66.0
—
MathMath problems.
54.1 best
52.7

Benchmarks

22 shared
Only Inkling: 56Only MiMo-V2.5: 6
Inkling
MiMo-V2.5
82.9% best64 / 149
78.9%101 / 149
TaxEval v2Finance
75.3% best19 / 143
71.8%72 / 143
85.5% best30 / 142
81.5%60 / 142
87.1% best40 / 135
81.6%61 / 135
MMLU ProKnowledge
86.3% best43 / 135
82.9%75 / 135
CorpFin v2Finance
68.6% best7 / 131
59.9%71 / 131
19.2%94 / 123
42.2% best75 / 123
MedScribeHealthcare
85.4% best28 / 109
72.2%90 / 109
MedCodeHealthcare
41.2% best56 / 106
31.9%91 / 106
64.0% best49 / 97
59.3%67 / 97
MMMU ProMultimodal
78.5%51 / 92
80.0% best45 / 92
28.4% best60 / 90
9.1%82 / 90
SWE-benchCoding
77.6% best34 / 87
71.0%60 / 87
54.3%57 / 83
56.1% best51 / 83
15.3% best61 / 82
7.8%71 / 82
46.6% best54 / 79
36.7%67 / 79
11.8%63 / 77
14.2% best57 / 77
EMBFinance
38.4%61 / 75
55.1% best50 / 75
47.6%63 / 75
60.7% best40 / 75
0.0%53 / 54
16.0% best46 / 54