DeepSeek-R1-0528 vs Grok 3 Mini

Change models
IndexAll categories, out of 100.
44.5 ±8.9 best
44.1 ±9.7
GapIndex points below the top.
Top
−0.4 · no clear gap
CoverageIndex weight that has results.
60%
60%
SpeedOutput tokens per second.
34/s
65/s best
EloLMArena rating and rank.
1428 best
1370
ReleasedMonth of release.
2025-05
2025-02
Input / 1MUS dollars per 1M input tokens.
$0.571
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$2.29
$0.50 best
1K chats2K tokens in, 500 out, each.
$2.29
$0.85 best
1K documents20K tokens in, 1K out, each.
$13.71
$6.50 best
1K agent tasks200K tokens in, 20K out, each.
$159.92
$70.00 best
ContextMaximum tokens in one request.
164K best
128K
AgenticMulti-step tasks with tools.
—
—
CodingCode writing and repair.
46.5
50.8 best
ReasoningLogic problems and puzzles.
38.3 best
37.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
45.7
48.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
46.2 best
43.8

Benchmarks

7 shared
Only DeepSeek-R1-0528: 6Only Grok 3 Mini: 6
DeepSeek-R1-0528
Grok 3 Mini
81.0% best65 / 144
80.3%66 / 144
1.1% best117 / 137
0.4%123 / 137
21.2% best109 / 132
16.5%113 / 132
0.3% best104 / 127
0.0%107 / 127
27.0% best99 / 116
17.6%103 / 116
91.4% best5 / 28
89.5%6 / 28
73.3%3 / 14
74.8% best2 / 14