DeepSeek V4.1 Flash 1017 vs Ling 3.1 Flash
Change models
Ling 3.1 FlashInclusionAI
IndexAll categories, out of 100.
68.5 ±2.6 best
67.2 ±7.2
GapIndex points below the top.
Top
−1.3 · no clear gap
CoverageIndex weight that has results.
95% best
70%
SpeedOutput tokens per second.
261/s best
81/s
EloLMArena rating and rank.
1463
—
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.022 best
$0.045
Output / 1MUS dollars per 1M output tokens.
$0.40
$0.135 best
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.244
$0.158 best
1K documents20K tokens in, 1K out, each.
$0.84 best
$1.04
1K agent tasks200K tokens in, 20K out, each.
$12.40
$11.70 best
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
72.2 best
66.6
CodingCode writing and repair.
69.8 best
66.9
ReasoningLogic problems and puzzles.
65.0
68.0 best
MultimodalTasks with images and text.
62.2
—
KnowledgeFacts and expert knowledge.
64.2
70.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.3
—
MathMath problems.
65.4
—
Benchmarks
10 sharedOnly DeepSeek V4.1 Flash 1017: 84Only Ling 3.1 Flash: 8
DeepSeek V4.1 Flash 1017
Ling 3.1 Flash