Inference
EN

Claude Sonnet 5.5 vs MiMo-V2.6-Pro

Change models
Claude Sonnet 5.5Anthropic
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
77.2 ±2.6 best
70.2 ±4.7
GapIndex points below the top.
Top
−7.0
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
107/s best
31/s
EloLMArena rating and rank.
1469
1492 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$50.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$104.40 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
77.5 best
72.1
CodingCode writing and repair.
80.8 best
66.6
ReasoningLogic problems and puzzles.
77.8 best
68.3
MultimodalTasks with images and text.
74.4
—
KnowledgeFacts and expert knowledge.
71.3 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
41.5
—
MathMath problems.
76.1 best
71.3

Benchmarks

46 shared
Only Claude Sonnet 5.5: 82Only MiMo-V2.6-Pro: 12
Claude Sonnet 5.5
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
55.0% best6 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
31.4% best7 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
51.5% best17 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
66.9% best4 / 133
59.2%9 / 133
Vibe Code Bench v1.1Coding
92.4% best2 / 123
85.2%16 / 123
Artificial Analysis SciCodeCoding
61.0% best6 / 114
60.9%8 / 114
MedScribeHealthcare
91.1% best3 / 109
88.3%13 / 109
MedCodeHealthcare
52.9% best12 / 106
45.0%39 / 106
Legal Research BenchLegal
48.1% best12 / 90
47.1%16 / 90
Tax Agent BenchFinance
42.0% best10 / 82
32.4%22 / 82
LiveBench Data AnalysisReasoning
59.5%73 / 80
72.3% best49 / 80
LiveBench ReasoningReasoning
91.6% best7 / 80
79.6%59 / 80
Finance Agent (v2)Finance
58.1% best12 / 79
57.3%16 / 79
Code MigrationCoding
69.8% best1 / 77
43.0%26 / 77
EMBFinance
75.7% best3 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
83.1% best6 / 75
67.8%32 / 75
ProgramBenchCoding
6.5% best4 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
64.1% best3 / 61
31.3%24 / 61
DeepSWEAgentic
71.0%21 / 59
71.9% best18 / 59