Inference
EN

GPT-6 Astra vs MiMo-V2.6-Pro

Change models
GPT-6 AstraOpenAI
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
78.0 ±1.9 best
70.2 ±4.7
GapIndex points below the top.
Top
−7.8
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
34/s best
31/s
EloLMArena rating and rank.
1440
1492 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$10.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$250.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
74.6 best
72.1
CodingCode writing and repair.
76.9 best
66.6
ReasoningLogic problems and puzzles.
83.8 best
68.3
MultimodalTasks with images and text.
71.2
—
KnowledgeFacts and expert knowledge.
78.5 best
64.2
MultilingualTasks in many languages.
73.6
—
InstructionTasks with strict prompt rules.
79.5
—
MathMath problems.
78.0 best
71.3

Benchmarks

49 shared
Only GPT-6 Astra: 89Only MiMo-V2.6-Pro: 9
GPT-6 Astra
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
54.7% best8 / 222
49.4%14 / 222
Artificial Analysis Long Context ReasoningReasoning
80.7%37 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
31.7% best4 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
61.6% best6 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
53.7%25 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
89.6% best8 / 123
85.2%16 / 123
Artificial Analysis SciCodeCoding
56.5%24 / 114
60.9% best8 / 114
MedScribeHealthcare
87.9%16 / 109
88.3% best13 / 109
MedCodeHealthcare
48.5% best29 / 106
45.0%39 / 106
Legal Research BenchLegal
39.4%37 / 90
47.1% best16 / 90
Tax Agent BenchFinance
20.7%52 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
83.0% best2 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
92.7% best2 / 80
79.6%59 / 80
Finance Agent (v2)Finance
53.5%33 / 79
57.3% best16 / 79
Code MigrationCoding
67.7% best3 / 77
43.0%26 / 77
EMBFinance
71.7% best11 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
87.3% best2 / 75
67.8%32 / 75
ProgramBenchCoding
5.5% best5 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
59.6% best5 / 61
31.3%24 / 61
DeepSWEAgentic
74.1% best11 / 59
71.9%18 / 59