DeepSeek V4 Pro 0813 vs Muse Spark 1.1

Change models
IndexAll categories, out of 100.
64.0 ±4.6 best
63.6 ±3.1
GapIndex points below the top.
Top
−0.4 · no clear gap
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
93/s
204/s best
EloLMArena rating and rank.
—
1479
ReleasedMonth of release.
2026-08
2026-07
Input / 1MUS dollars per 1M input tokens.
$1.32
$1.25 best
Output / 1MUS dollars per 1M output tokens.
$3.96 best
$4.25
Batch output / 1MBatch price per 1M output tokens.
$1.98
—
1K chats2K tokens in, 500 out, each.
$4.62 best
$4.63
1K documents20K tokens in, 1K out, each.
$30.36
$29.25 best
1K agent tasks200K tokens in, 20K out, each.
$343.20
$335.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
58.5
60.7 best
CodingCode writing and repair.
65.3 best
63.9
ReasoningLogic problems and puzzles.
67.5 best
61.9
MultimodalTasks with images and text.
—
66.2
KnowledgeFacts and expert knowledge.
62.0
66.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
62.7
66.4 best
MathMath problems.
64.3 best
60.4

Benchmarks

25 shared
Only DeepSeek V4 Pro 0813: 21Only Muse Spark 1.1: 34
DeepSeek V4 Pro 0813
Muse Spark 1.1
82.4%72 / 149
85.0% best27 / 149
TaxEval v2Finance
73.1%52 / 143
79.7% best2 / 143
87.5% best13 / 142
85.9%25 / 142
92.4% best16 / 135
91.2%23 / 135
MMLU ProKnowledge
87.0%35 / 135
88.7% best17 / 135
CorpFin v2Finance
65.4%27 / 131
71.3% best4 / 131
82.3% best30 / 130
72.2%53 / 130
MedScribeHealthcare
80.2%61 / 111
88.9% best10 / 111
40.9% best38 / 98
38.0%49 / 98
52.9%29 / 94
57.8% best23 / 94
Chess PuzzlesReasoning
46.0% best29 / 93
34.0%50 / 93
SWE-benchCoding
96.4% best2 / 87
82.0%21 / 87
79.2% best19 / 80
72.5%48 / 80
85.8%35 / 80
87.7% best27 / 80
50.4%44 / 79
57.2% best17 / 79
41.5% best28 / 77
31.1%39 / 77
EMBFinance
52.8%53 / 75
56.4% best45 / 75
54.7%51 / 75
69.3% best30 / 75
54.9%29 / 66
58.5% best18 / 66
77.2%37 / 66
77.2%37 / 66