DeepSeek V4.1 Flash 1017 vs Qwen4 Max
Change modelsDeepSeek V4.1 Flash 1017DeepSeek
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
68.1 ±2.6
72.0 ±8.0 best
GapIndex points below the top.
−3.9 · no clear gap
Top
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
102/s best
40/s
EloLMArena rating and rank.
1464
—
ReleasedMonth of release.
2026-10
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.14 best
$1.50
Output / 1MUS dollars per 1M output tokens.
$0.42 best
$4.50
Batch output / 1MBatch price per 1M output tokens.
$0.31
—
1K chats2K tokens in, 500 out, each.
$0.49 best
$5.25
1K documents20K tokens in, 1K out, each.
$3.22 best
$34.50
1K agent tasks200K tokens in, 20K out, each.
$36.40 best
$390.00
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
71.8
75.2 best
CodingCode writing and repair.
69.3 best
67.0
ReasoningLogic problems and puzzles.
64.8
—
MultimodalTasks with images and text.
61.8
72.1 best
KnowledgeFacts and expert knowledge.
63.9
70.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.0
—
MathMath problems.
65.1
—
Benchmarks
9 sharedOnly DeepSeek V4.1 Flash 1017: 87Only Qwen4 Max: 10
DeepSeek V4.1 Flash 1017
Qwen4 Max