Inference
EN

DeepSeek V4.1 Flash 1017 vs Muse Wonder

Change models
DeepSeek V4.1 Flash 1017DeepSeekFastest
Muse WonderMeta
IndexAll categories, out of 100.
68.5 ±2.6
73.1 ±4.0 best
GapIndex points below the top.
−4.6 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
261/s best
80/s
EloLMArena rating and rank.
1463
1503 best
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.022 best
$4.00
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$20.00
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.244 best
$18.00
1K documents20K tokens in, 1K out, each.
$0.84 best
$100.00
1K agent tasks200K tokens in, 20K out, each.
$12.40 best
$1,200.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
72.2
73.0 best
CodingCode writing and repair.
69.8
72.3 best
ReasoningLogic problems and puzzles.
65.0
73.1 best
MultimodalTasks with images and text.
62.2
—
KnowledgeFacts and expert knowledge.
64.2
68.6 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.3
74.4 best
MathMath problems.
65.4
73.5 best

Benchmarks

49 shared
Only DeepSeek V4.1 Flash 1017: 45Only Muse Wonder: 13
DeepSeek V4.1 Flash 1017
Muse Wonder
Artificial Analysis Humanity's Last ExamKnowledge
39.2%51 / 222
50.1% best12 / 222
Artificial Analysis Long Context ReasoningReasoning
84.0% best8 / 217
80.7%37 / 217
Critical Physics TasksReasoning
14.3%52 / 214
28.3% best15 / 214
OTIS Mock AIME 2024-2025Math
98.3%28 / 200
99.4% best17 / 200
Artificial Analysis Omniscience AccuracyKnowledge
46.4% best33 / 164
38.0%59 / 164
GDPval-AA normalizedAgentic
55.0%21 / 133
63.5% best5 / 133
Vibe Code Bench v1.1Coding
84.7% best18 / 123
83.1%22 / 123
Artificial Analysis SciCodeCoding
51.9%44 / 114
60.3% best10 / 114
FrontierMath-Tiers-1-3-v2-PrivateMath
67.4%33 / 90
82.1% best18 / 90
Legal Research BenchLegal
41.3%30 / 90
50.5% best7 / 90
Tax Agent BenchFinance
26.6%41 / 82
36.3% best15 / 82
LiveBench Data AnalysisReasoning
79.3%15 / 80
81.6% best5 / 80
LiveBench ReasoningReasoning
86.7%31 / 80
90.6% best11 / 80
Mystery Game PuzzlesReasoning
43.0%17 / 80
51.0% best15 / 80
Finance Agent (v2)Finance
53.5%33 / 79
56.6% best18 / 79
Code MigrationCoding
45.6%17 / 77
62.6% best6 / 77
EMBFinance
57.2%40 / 75
67.1% best18 / 75
FrontierMath-Tier-4-v2-PrivateMath
26.8%39 / 72
70.7% best17 / 72
LiveBench Agentic CodingAgentic
77.3% best1 / 66
62.7%9 / 66
LiveBench CodingCoding
80.0%20 / 66
80.7% best16 / 66