Inference
EN

Claude Opus 5.5 vs MiMo-V2.6-Pro

Change models
Claude Opus 5.5Anthropic
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
78.6 ±2.4 best
70.2 ±4.7
GapIndex points below the top.
Top
−8.4
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
76/s best
31/s
EloLMArena rating and rank.
1513 best
1492
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$4.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$20.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
—
1K chats2K tokens in, 500 out, each.
$18.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$100.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$1,200.00
$104.40 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
74.1 best
72.1
CodingCode writing and repair.
81.8 best
66.6
ReasoningLogic problems and puzzles.
80.8 best
68.3
MultimodalTasks with images and text.
74.1
—
KnowledgeFacts and expert knowledge.
79.2 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
59.6
—
MathMath problems.
77.7 best
71.3

Benchmarks

53 shared
Only Claude Opus 5.5: 104Only MiMo-V2.6-Pro: 5
Claude Opus 5.5
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
61.4% best2 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
84.7%6 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
31.7% best4 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
65.5% best3 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
68.3% best1 / 133
59.2%9 / 133
Vibe Code Bench v1.1Coding
90.3% best6 / 123
85.2%16 / 123
Artificial Analysis SciCodeCoding
66.9% best2 / 114
60.9%8 / 114
MedScribeHealthcare
91.4% best1 / 109
88.3%13 / 109
MedCodeHealthcare
49.8% best19 / 106
45.0%39 / 106
Legal Research BenchLegal
50.5% best7 / 90
47.1%16 / 90
Tax Agent BenchFinance
44.5% best6 / 82
32.4%22 / 82
LiveBench Data AnalysisReasoning
80.3% best9 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
92.2% best4 / 80
79.6%59 / 80
Finance Agent (v2)Finance
58.6% best10 / 79
57.3%16 / 79
Code MigrationCoding
66.6% best4 / 77
43.0%26 / 77
EMBFinance
75.9% best2 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
87.6% best1 / 75
67.8%32 / 75
ProgramBenchCoding
18.5% best2 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
65.2% best1 / 61
31.3%24 / 61
DeepSWEAgentic
74.2% best10 / 59
71.9%18 / 59