TAU2
Measured Jul 10, 2026Source
Score
0.94
Models11 2 
Qwen3.5 27B (Reasoning)
阿里巴巴阿里巴巴China
Qwen3.5 27B (Reasoning) is a 27-billion parameter language model from Alibaba, optimized for reasoning tasks with enhanced chain-of-thought capabilities. It is designed for complex problem-solving and logical inference.
ReasoningCodingLong context
Input / 1M tokens
$0.30Output / 1M tokens
$2.40Output tokens/s
83.93First-token seconds
1.4sSupported plans
11Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.33
Lcr
Measured Jul 10, 2026Source
Score
0.67
Ifbench
Measured Jul 10, 2026Source
Score
0.76
Scicode
Measured Jul 10, 2026Source
Score
0.4
Hle
Measured Jul 10, 2026Source
Score
0.22
Gpqa
Measured Jul 10, 2026Source
Score
0.86
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
33.8
Terminalbench V2 1
Measured Jul 10, 2026Source
Score
0.51
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
48.2
Tau Banking
Measured Jul 10, 2026Source
Score
0.14
Plan availability
Products and plans that support this model
Apertis Coding Plan
Apertis Coding Plan
Apertis Coding Plan is a subscription-based AI coding service providing unified access to 30+ AI models (GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, and more) through a single API key. Designed for developers using coding agents like Claude Code, Cursor, Cline, and OpenCode, it offers predictable monthly pricing, free prompt caching, auto-failover, and quota-based billing across OpenAI, Anthropic, Google, and other providers.
Arli
Arli
Arli AI is an unrestricted AI inference platform providing access to multiple LLMs and image generation models via an OpenAI-compatible API, with subscription plans for unlimited usage and no rate limits.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server