Claude 4.1 Opus Thinking vs MiMo-V2-Omni
Change modelsClaude 4.1 Opus ThinkingAnthropic
MiMo-V2-OmniXiaomi
IndexAll categories, out of 100.
47.0 ±9.2
47.2 ±6.6 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
65%
85% best
SpeedOutput tokens per second.
29/s
—
EloLMArena rating and rank.
—
1423
ReleasedMonth of release.
2025-08
2026-03
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
200K
262K best
AgenticMulti-step tasks with tools.
50.2 best
46.9
CodingCode writing and repair.
—
56.4
ReasoningLogic problems and puzzles.
48.1
48.9 best
MultimodalTasks with images and text.
43.5
46.1 best
KnowledgeFacts and expert knowledge.
47.9 best
44.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
40.8 best
39.0
MathMath problems.
—
—
Benchmarks
7 sharedOnly Claude 4.1 Opus Thinking: 1Only MiMo-V2-Omni: 3
Claude 4.1 Opus Thinking
MiMo-V2-Omni