Inference
EN

GPT-5.6 Sol vs MiMo-V2.6-Pro

Change models
GPT-5.6 SolOpenAI
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
73.0 ±1.9 best
70.2 ±4.7
GapIndex points below the top.
Top
−2.8 · no clear gap
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
64/s best
31/s
EloLMArena rating and rank.
1457
1492 best
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$4.40
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$22.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
—
1K chats2K tokens in, 500 out, each.
$19.80
$1.31 best
1K documents20K tokens in, 1K out, each.
$110.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$1,320.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
71.9
72.1 best
CodingCode writing and repair.
70.4 best
66.6
ReasoningLogic problems and puzzles.
76.3 best
68.3
MultimodalTasks with images and text.
72.6
—
KnowledgeFacts and expert knowledge.
72.7 best
64.2
MultilingualTasks in many languages.
66.4
—
InstructionTasks with strict prompt rules.
64.5
—
MathMath problems.
75.1 best
71.3

Benchmarks

40 shared
Only GPT-5.6 Sol: 85Only MiMo-V2.6-Pro: 18
GPT-5.6 Sol
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
49.5% best13 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
84.0%8 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
32.3% best3 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
59.4% best8 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
55.4%19 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
80.5%31 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
57.1%22 / 114
60.9% best8 / 114
MedScribeHealthcare
85.2%31 / 109
88.3% best13 / 109
MedCodeHealthcare
44.0%43 / 106
45.0% best39 / 106
Legal Research BenchLegal
48.1% best12 / 90
47.1%16 / 90
Terminal-Bench 2.1 · BenchLMAgentic
91.9% best2 / 86
89.9%4 / 86
Tax Agent BenchFinance
31.1%29 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
79.8% best12 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
91.7% best5 / 80
79.6%59 / 80
Finance Agent (v2)Finance
53.8%31 / 79
57.3% best16 / 79
Code MigrationCoding
52.9% best12 / 77
43.0%26 / 77
EMBFinance
72.3% best7 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
85.8% best3 / 75
67.8%32 / 75
ProgramBenchCoding
1.5% best14 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
37.9% best19 / 61
31.3%24 / 61