DeepSeek-R1 vs LongCat-Flash-Lite-Sparse

Change models
DeepSeek-R1DeepSeek
IndexAll categories, out of 100.
38.8 ±5.0
39.1 ±7.8 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
85% best
65%
SpeedOutput tokens per second.
18/s
—
EloLMArena rating and rank.
1373
—
ReleasedMonth of release.
2025-01
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.70
—
Output / 1MUS dollars per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$2.65
—
1K documents20K tokens in, 1K out, each.
$16.50
—
1K agent tasks200K tokens in, 20K out, each.
$190.00
—
ContextMaximum tokens in one request.
64K
1M best
AgenticMulti-step tasks with tools.
28.2
39.2 best
CodingCode writing and repair.
42.3
47.2 best
ReasoningLogic problems and puzzles.
39.7
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
43.4 best
39.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
28.8
—
MathMath problems.
43.5 best
32.8

Benchmarks

4 shared
Only DeepSeek-R1: 30Only LongCat-Flash-Lite-Sparse: 11
DeepSeek-R1
LongCat-Flash-Lite-Sparse
49.2%99 / 114
68.2% best77 / 114
84.0% best24 / 73
79.2%37 / 73
90.8% best2 / 35
85.3%19 / 35
97.3% best8 / 29
95.8%16 / 29