AI Benchmark Model
GLM-5.1 (Reasoning)
Benchmark scores, pricing, speed, and model comparisons for GLM-5.1 (Reasoning).
Key scores
GLM-5.1 (Reasoning) is an AI model developed by Z AI and released on April 7, 2026. The model achieves an intelligence index of 51.4 and a coding index of 43.4. Performance metrics indicate an output speed of 54.406 tokens per second with a time to first token of 0.929 seconds. Benchmark results for the model include 0.868 on GPQA, 0.28 on HLE, 0.438 on SciCode, 0.7626 on IFBench, 0.6233 on LCR, 0.4318 on TerminalBench Hard, and 0.9766 on TAU2. Pricing for GLM-5.1 is set at $1.40 per 1 million input tokens and $4.40 per 1 million output tokens, resulting in a blended cost of $2.15 per 1 million tokens.
Benchmark results
7 tracked benchmark rows for GLM-5.1 (Reasoning).
TAU2 Other
97.7% GPQA Reasoning
86.8% IFBench Other
76.3% LCR Other
62.3% SciCode Other
43.8% TerminalBench Hard Other
43.2% HLE Other
28.0%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!