Inference
EN

DeepSeek V4.1 Flash 1017 vs MiMo-V2.6-Pro

Change models
DeepSeek V4.1 Flash 1017DeepSeekFastest
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
68.5 ±2.6
70.2 ±4.7 best
GapIndex points below the top.
−1.7 · no clear gap
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
261/s best
31/s
EloLMArena rating and rank.
1463
1492 best
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.022 best
$0.435
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$0.87
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.244 best
$1.31
1K documents20K tokens in, 1K out, each.
$0.84 best
$9.57
1K agent tasks200K tokens in, 20K out, each.
$12.40 best
$104.40
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
72.2 best
72.1
CodingCode writing and repair.
69.8 best
66.6
ReasoningLogic problems and puzzles.
65.0
68.3 best
MultimodalTasks with images and text.
62.2
—
KnowledgeFacts and expert knowledge.
64.2
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.3
—
MathMath problems.
65.4
71.3 best

Benchmarks

48 shared
Only DeepSeek V4.1 Flash 1017: 46Only MiMo-V2.6-Pro: 10
DeepSeek V4.1 Flash 1017
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
39.2%51 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
84.0%8 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
14.3%52 / 214
26.6% best19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
46.4% best33 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
55.0%21 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
84.7%18 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
51.9%44 / 114
60.9% best8 / 114
MedScribeHealthcare
85.5%27 / 109
88.3% best13 / 109
MedCodeHealthcare
41.2%56 / 106
45.0% best39 / 106
Legal Research BenchLegal
41.3%30 / 90
47.1% best16 / 90
Terminal-Bench 2.1 · BenchLMAgentic
90.6% best3 / 86
89.9%4 / 86
Tax Agent BenchFinance
26.6%41 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
79.3% best15 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
86.7% best31 / 80
79.6%59 / 80
Finance Agent (v2)Finance
53.5%33 / 79
57.3% best16 / 79
Code MigrationCoding
45.6% best17 / 77
43.0%26 / 77
EMBFinance
57.2%40 / 75
62.9% best30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
74.5% best18 / 75
67.8%32 / 75
ProgramBenchCoding
0.5%19 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
19.7%34 / 61
31.3% best24 / 61