Inference
EN

DeepSeek V4.1 Flash 1017 vs Muse Wonder Full

Change models
DeepSeek V4.1 Flash 1017DeepSeekFastest
Muse Wonder FullMeta
IndexAll categories, out of 100.
68.5 ±2.6
77.3 ±5.3 best
GapIndex points below the top.
−8.8
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
261/s
—
EloLMArena rating and rank.
1463
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.022
—
Output / 1MUS dollars per 1M output tokens.
$0.40
—
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.244
—
1K documents20K tokens in, 1K out, each.
$0.84
—
1K agent tasks200K tokens in, 20K out, each.
$12.40
—
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
72.2
78.2 best
CodingCode writing and repair.
69.8
77.3 best
ReasoningLogic problems and puzzles.
65.0
75.6 best
MultimodalTasks with images and text.
62.2
—
KnowledgeFacts and expert knowledge.
64.2
71.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.3
—
MathMath problems.
65.4
79.6 best

Benchmarks

32 shared
Only DeepSeek V4.1 Flash 1017: 62Only Muse Wonder Full: 10
DeepSeek V4.1 Flash 1017
Muse Wonder Full
Artificial Analysis Humanity's Last ExamKnowledge
39.2%51 / 222
53.6% best9 / 222
Artificial Analysis Long Context ReasoningReasoning
84.0% best8 / 217
83.7%10 / 217
Critical Physics TasksReasoning
14.3%52 / 214
32.9% best2 / 214
Artificial Analysis Omniscience AccuracyKnowledge
46.4% best33 / 164
41.0%46 / 164
LegalBenchLegal
83.3%56 / 149
87.4% best4 / 149
GDPval-AA normalizedAgentic
55.0%21 / 133
67.9% best2 / 133
Vibe Code Bench v1.1Coding
84.7%18 / 123
86.0% best14 / 123
Artificial Analysis SciCodeCoding
51.9%44 / 114
62.6% best4 / 114
MedScribeHealthcare
85.5%27 / 109
89.3% best8 / 109
MedCodeHealthcare
41.2%56 / 106
49.9% best18 / 106
Legal Research BenchLegal
41.3%30 / 90
53.4% best6 / 90
Tax Agent BenchFinance
26.6%41 / 82
43.0% best8 / 82
Finance Agent (v2)Finance
53.5%33 / 79
59.1% best6 / 79
Code MigrationCoding
45.6%17 / 77
61.0% best7 / 77
EMBFinance
57.2%40 / 75
71.9% best10 / 75
ProgramBenchCoding
0.5%19 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
19.7%34 / 61
58.1% best6 / 61
DeepSWEAgentic
77.0%4 / 59
79.0% best1 / 59
Agent Arena steerabilityAgentic
4.018 / 54
9.6 best12 / 54
Agent Arena task outcomeAgentic
2.325 / 54
11.1 best9 / 54