Claude Opus 4.5 Thinking vs MiniMax M3
Change modelsClaude Opus 4.5 ThinkingAnthropic
MiniMax M3MiniMax
IndexAll categories, out of 100.
56.3 ±4.2 best
55.7 ±2.9
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
79/s
EloLMArena rating and rank.
—
1428
ReleasedMonth of release.
2025-11
2026-06
Input / 1MUS dollars per 1M input tokens.
—
$0.30
Output / 1MUS dollars per 1M output tokens.
—
$1.20
Batch output / 1MBatch price per 1M output tokens.
—
$0.88
1K chats2K tokens in, 500 out, each.
—
$1.20
1K documents20K tokens in, 1K out, each.
—
$7.20
1K agent tasks200K tokens in, 20K out, each.
—
$84.00
ContextMaximum tokens in one request.
200K
1.05M best
AgenticMulti-step tasks with tools.
59.7 best
57.4
CodingCode writing and repair.
54.4
57.7 best
ReasoningLogic problems and puzzles.
54.2 best
50.5
MultimodalTasks with images and text.
57.3 best
56.5
KnowledgeFacts and expert knowledge.
59.0
61.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
43.2
54.7 best
MathMath problems.
57.2 best
41.6
Benchmarks
21 sharedOnly Claude Opus 4.5 Thinking: 16Only MiniMax M3: 63
Claude Opus 4.5 Thinking
MiniMax M3