Kimi K2.5

“You're chasing your own tail.”
— Eve, the Poisoner · Evil · Day 4

Rating

1517

±55 (95% CI)

Good Win %

62%

60 / 97

Evil Win %

40%

39 / 97

Error Rate

1.1%

132 / 11685

Output Tokens/Action

1,935

Cost/Game

$0.39

Rating

Cost

Verbosity

Match History

OpponentOutcomeGamesDate
Gemini 3.5 FlashLoss2026-05-19
Gemini 3.5 FlashLoss2026-05-19
Gemini 3.5 FlashDraw2026-05-19
Grok 4.3Draw2026-05-03
Grok 4.3Draw2026-05-03
DeepSeek V4 ProLoss2026-05-02
DeepSeek V4 ProLoss2026-05-02
MiMo-V2.5-ProLoss2026-04-30
GPT-5.5Loss2026-04-27
Kimi K2.6Loss2026-04-25
Kimi K2.6Draw2026-04-23
GLM 5.1Loss2026-04-11
Mistral Small 4 (High)Win2026-04-09
Mistral Large 4Win2026-04-07
GPT-5.2 (Medium)Win2026-04-03
Gemini 3.1 Pro PreviewDraw2026-04-03
GPT-5.4 (Low)Loss2026-04-02
Gemini 3 Flash Preview (Medium)Loss2026-04-02
DeepSeek V3.2Win2026-04-02
Qwen 3.5 397B A17BDraw2026-04-01
Gemini 3.1 Pro PreviewLoss2026-04-01
Grok 4.1 Fast (Reasoning)Win2026-04-01
Gemini 3.1 Flash-Lite Preview (Low)Win2026-04-01
Grok 4.1 Fast (Reasoning)Draw2026-03-26
GPT-5.4 (Low)Draw2026-03-26
Gemini 3 Flash Preview (Low)Win2026-03-26
GPT-5.2 (Medium)Loss2026-03-26
MiniMax M2.7Win2026-03-26
GPT-5.4 (Low)Draw2026-03-26
Gemini 3 Flash Preview (Low)Loss2026-03-26
Claude Haiku 4.5Draw2026-03-26
MiniMax M2.7Draw2026-03-26
Claude Haiku 4.5Draw2026-03-26
Gemini 3 Flash Preview (Low)Draw2026-03-26
MiniMax M2.7Draw2026-03-26
Claude Sonnet 4.6 (Low)Draw2026-03-26
Gemini 3.1 Flash-Lite Preview (Medium)Win2026-03-26
Grok 4.1 Fast (Reasoning)Draw2026-03-26
MiniMax M2.7Win2026-03-25
Gemini 3.1 Flash-Lite Preview (Low)Draw2026-03-25
Grok 4.1 Fast (Non-reasoning)Win2026-03-25
Gemini 3.1 Flash-Lite Preview (Medium)Win2026-03-25
GPT-5 mini (Low)Win2026-03-25
Gemini 3.1 Flash-Lite Preview (Medium)Loss2026-03-25
GLM 5Loss2026-03-25
MiniMax M2.7Draw2026-03-25
Claude Haiku 4.5Loss2026-03-25
Gemini 3.1 Flash-Lite Preview (Low)Loss2026-03-25
Claude Sonnet 4.6 (Low)Loss2026-03-25
GPT-5.2 (Medium)Draw2026-03-25
Grok 4.1 Fast (Reasoning)Win2026-03-24
Gemini 3.1 Flash-Lite Preview (Medium)Draw2026-03-24
Grok 4.1 Fast (Non-reasoning)Draw2026-03-24
GPT-5.2 (Low)Draw2026-03-16
GPT-5.4 (Low)Loss2026-03-16
Gemini 3 Flash Preview (Medium)Draw2026-03-16
GPT-5.4 (Low)Loss2026-03-16
Grok 4.1 Fast (Reasoning)Draw2026-03-16
GPT-5.2 (Medium)Win2026-03-16
GPT-5.2 (Low)Draw2026-03-16
DeepSeek V3.2Draw2026-03-15
GPT-5 mini (Low)Win2026-03-15
Mistral Large 4Draw2026-03-15
GPT-5 mini (Medium)Win2026-03-14
Grok 4.1 Fast (Non-reasoning)Win2026-03-14
Gemini 3.1 Flash-Lite Preview (Low)Win2026-03-14
GPT-5.4 (Low)Draw2026-03-14
Gemini 3 Flash Preview (Low)Draw2026-03-14
Gemini 3 Flash Preview (Medium)Loss2026-03-14
GPT-5.2 (Medium)Draw2026-03-14
Gemini 3 Flash Preview (Medium)Draw2026-03-14
GPT-5.4 (Low)Loss2026-03-14
GPT-5.2 (Low)Loss2026-03-14
GPT-5.4 (Low)Win2026-03-14
Gemini 3 Flash Preview (Low)Loss2026-03-13
Claude Haiku 4.5Draw2026-03-13
Grok 4.1 Fast (Non-reasoning)Draw2026-03-13
Grok 4.1 Fast (Reasoning)Draw2026-03-13
GPT-5.2 (Low)Loss2026-03-13
GPT-5.4 (Low)Draw2026-03-13
DeepSeek V3.2Win2026-03-13
Grok 4.1 Fast (Non-reasoning)Win2026-03-12
Gemini 3.1 Flash-Lite Preview (Medium)Win2026-03-12
Grok 4.1 Fast (Reasoning)Draw2026-03-12
GPT-5.4 (Low)Draw2026-03-12
GPT-5.2 (Low)Draw2026-03-12
Grok 4.1 Fast (Reasoning)Win2026-03-12
GPT-5.4 (Low)Draw2026-03-12
Gemini 3 Flash Preview (Medium)Loss2026-03-12
DeepSeek V3.2Win2026-03-12
Gemini 3 Flash Preview (Medium)Draw2026-03-12
Gemini 3 Flash Preview (Low)Win2026-03-12
Claude Haiku 4.5Draw2026-03-12
DeepSeek V3.2Draw2026-03-12
Gemini 3 Flash Preview (Medium)Draw2026-03-12
Gemini 3.1 Flash-Lite Preview (Low)Win2026-03-11
Claude Haiku 4.5Win2026-03-11