TAU2
Measured Jul 10, 2026Source
Score
0.81
Models8 2 
Kimi K2.5 (Non-reasoning)
KimiKimiChina
Kimi K2.5 (Non-reasoning) is a fast-response variant of the Kimi K2.5 series, optimized for low-latency interactions. It excels in rapid content generation, chat, and multimodal understanding tasks where immediate answers are prioritized over deep, step-by-step reasoning.
FastMultimodalLong context
Input / 1M tokens
$0.60Output / 1M tokens
$3.00Output tokens/s
38.1First-token seconds
1.3sSupported plans
10Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.19
Lcr
Measured Jul 10, 2026Source
Score
0.59
Ifbench
Measured Jul 10, 2026Source
Score
0.44
Scicode
Measured Jul 10, 2026Source
Score
0.4
Hle
Measured Jul 10, 2026Source
Score
0.12
Gpqa
Measured Jul 10, 2026Source
Score
0.79
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
29.4
Plan availability
Products and plans that support this model
Crof AI Plan
Crof AI Plan
CrofAI is a cost-effective AI inference API platform that provides access to various open-source large language models (LLMs) such as DeepSeek, GLM, and Qwen through an OpenAI-compatible API. It offers tiered subscription plans and pay-as-you-go pricing for developers and businesses.
Neuralwatt
Neuralwatt
Neuralwatt Cloud is an AI inference API with energy-based pricing, providing OpenAI-compatible access to multiple models from providers like Mistral, ZhipuAI, OpenAI, Kimi, MiniMax, and Qwen, with real-time energy tracking.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server