Inference
EN

GPT-5.5 vs MiMo-V2.6-Pro

Change models
GPT-5.5OpenAI
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
69.1 ±2.5
70.2 ±4.7 best
GapIndex points below the top.
−1.1 · no clear gap
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
52/s best
31/s
EloLMArena rating and rank.
1466
1492 best
ReleasedMonth of release.
2026-04
2026-09
Input / 1MUS dollars per 1M input tokens.
$5.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$30.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$15.00
—
1K chats2K tokens in, 500 out, each.
$25.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$130.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$1,600.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.8
72.1 best
CodingCode writing and repair.
65.5
66.6 best
ReasoningLogic problems and puzzles.
74.1 best
68.3
MultimodalTasks with images and text.
66.8
—
KnowledgeFacts and expert knowledge.
70.4 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.8
—
MathMath problems.
74.7 best
71.3

Benchmarks

31 shared
Only GPT-5.5: 81Only MiMo-V2.6-Pro: 27
GPT-5.5
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
45.8%26 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
84.3%7 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
27.1% best17 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
58.0% best10 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
42.5%44 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
69.8%50 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
55.8%27 / 114
60.9% best8 / 114
MedScribeHealthcare
86.9%19 / 109
88.3% best13 / 109
MedCodeHealthcare
49.1% best26 / 106
45.0%39 / 106
Legal Research BenchLegal
40.4%35 / 90
47.1% best16 / 90
Tax Agent BenchFinance
21.8%49 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
81.6% best5 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
89.7% best15 / 80
79.6%59 / 80
Finance Agent (v2)Finance
51.8%39 / 79
57.3% best16 / 79
Code MigrationCoding
45.2% best18 / 77
43.0%26 / 77
EMBFinance
64.5% best26 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
76.4% best16 / 75
67.8%32 / 75
ProgramBenchCoding
0.5%19 / 65
0.5%19 / 65
LiveBench Coding 2.0Coding
85.1% best23 / 52
81.5%30 / 52
LiveBench DesignAgentic
70.3%39 / 52
78.5% best18 / 52