Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Moonshot AI · Active

kimi-k2.5-instant

kimi-thinking family · launched 2024-11-01

ReasoningToolsStructured
AITopic score48.3Not yet ranked

Kimi reasoning model for long-horizon research, planning, and tool use

Evidence coverage5%1 evaluations · 1 institutions
Context / maximum output32.8k / 4.1ktokens
Cache / input / output$0.28 · $0.55 · $2.25USD per million tokens
Value / freshness51.4 / 21relative value · release freshness
Product profile

What this model supports

Inputtext
Outputtext
Knowledge cutoff2024-08
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding—0 public results
Research & reasoning—0 public results
Professional work—0 public results
Knowledge & instruction—0 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Human preference & indices2 results

AA IndexArtificial Analysis62.08 indexReading 48.3

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: kimi-k2.5-instantOpen evidence
Arena TextLMArena1,420.1 EloReading 48.3

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from Moonshot AI