DeepSeek V3.2 (Thinking) vs MiniMax M2.1
Change modelsDeepSeek V3.2 (Thinking)DeepSeek
MiniMax M2.1MiniMax
IndexAll categories, out of 100.
49.4 ±8.6 best
49.1 ±8.9
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
65%
65%
SpeedOutput tokens per second.
—
34/s
EloLMArena rating and rank.
1420
—
ReleasedMonth of release.
2025-12
2025-12
Input / 1MUS dollars per 1M input tokens.
$0.55
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$2.19
$1.20 best
1K chats2K tokens in, 500 out, each.
$2.20
$1.20 best
1K documents20K tokens in, 1K out, each.
$13.19
$7.20 best
1K agent tasks200K tokens in, 20K out, each.
$153.80
$84.00 best
ContextMaximum tokens in one request.
128K
205K best
AgenticMulti-step tasks with tools.
47.7
48.5 best
CodingCode writing and repair.
49.2
51.6 best
ReasoningLogic problems and puzzles.
—
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
51.2
51.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
51.0 best
43.9
Benchmarks
15 sharedOnly DeepSeek V3.2 (Thinking): 2Only MiniMax M2.1: 3
DeepSeek V3.2 (Thinking)
MiniMax M2.1