Moonshot AI · mit

Kimi K2-Thinking-0905

Kimi K2-Thinking-0905 by Moonshot AI appears in 1 source with Reasoning at 45.23. Best read for Code quality, Math, Open weights.

CreatorMoonshot AI

Release date2025-09-05

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank51ranking · source_rank

Reasoning45.23reasoning · index_reasoning

Math47.05math · index_math

Coding25.93coding · index_code

Research19.83research · index_search

Writing-6.33writing · index_communication

Vision36.53multimodal · index_vision

Finance26.07domain · index_finance

Legal25.98domain · index_legal

Healthcare39.09domain · index_healthcare

GPQA84.5 %reasoning · gpqa_score

AIME 2025100 %math · aime_2025_score

SWE-bench Verified71.3 %coding · swe_bench_verified_score

Code Arena940.55 %coding · coding_arena_score

Humanity Last Exam51 %reasoning · hle_score

BrowseComp60.2 %research · browsecomp_score

Terminal Bench47.1 %coding · terminal_bench_score

SciCode44.8 %coding · scicode_score

Parameters1,000,000,000,000 paramsmodel · params

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Kimi K2-Thinking-0905 verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.