Kimi K2.5 Thinking

Released2026-01-27
Price per 1M$0.60 in · $3.00 out
Overall score52.7 · rank 232
Context window262,144 tokens
ProviderMoonshot AI
WeightsOpen weights
ConfigurationThinking

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 52.7 232 16
Overall: Coding 52.0 237 8
Overall: Reasoning 53.2 219 6
Overall: Agentic work 52.3 242 6
Overall: Frontend 48.6 236 6
Coding 53.7 204 2
Agents 50.8 196 1
Reasoning 56.0 187 3
Math 50.9 169 1
Knowledge 51.0 118 2
Frontend 44.7 153 2
General 55.0 117 3
Multimodal 56.3 62 2
Value vs price+2.1190

Evidence

Coding 53.7 ±3.3

BenchmarkResultSourceDate
SWE-bench Verified (Vals run) 70.0% Vals AI 2026-09-01
LiveCodeBench (Vals run) 83.9% Vals AI 2026-09-01

Agents 50.8 ±3.4

BenchmarkResultSourceDate
Terminal-Bench 2.1 (Vals run) 41.9% Vals AI 2026-10-01

Reasoning 56.0 ±4.3

BenchmarkResultSourceDate
Extended NYT Connections 69.9% Lech Mazur 2026-11-10
GPQA Diamond (Vals run) 84.1% Vals AI 2026-09-01
Kagi Reasoning Benchmark 78.5% Kagi 2026-11-11

Math 50.9 ±4.2

BenchmarkResultSourceDate
MathArena Final-Answer Competitions 62.3% MathArena 2026-11-11

Knowledge 51.0 ±3.9

BenchmarkResultSourceDate
MMLU-Pro (Vals run) 85.9% Vals AI 2026-09-01
Legal Research Bench 15.9% Vals AI 2026-11-09

Frontend 44.7 ±0.7

BenchmarkResultSourceDate
Vibe Code Bench v1.1 17.5% Vals AI 2026-11-09
LMArena WebDev 1,436 LMArena 2026-11-09

General 55.0 ±2.8

BenchmarkResultSourceDate
LMArena Text 1,450 LMArena 2026-11-09
LLM Debate Benchmark 1,445 Lech Mazur 2026-10-26
Creative Story-Writing (Lech Mazur) 33.0% Lech Mazur 2026-10-23

Multimodal 56.3 ±2.3

BenchmarkResultSourceDate
MMMU-Pro (Vals run) 84.3% Vals AI 2026-09-01
LMArena Vision 1,252 LMArena 2026-11-09

Names matched to this model

kimi-k2-5-thinking

Compare Kimi K2.5 Thinking with other models