AI Benchmark Model
GLM-5.3 (max)
Benchmark scores, pricing, speed, and model comparisons for GLM-5.3 (max).
Key scores
GLM-5.3 (max) is an artificial intelligence model developed by Z AI and released on August 18, 2026. The model demonstrates an intelligence index of 59.5 and a coding index of 74.8. Performance metrics indicate an output speed of 79.593 tokens per second with a time to first token of 1.507 seconds. Pricing for the model is set at $1.40 per million tokens for input and $4.40 per million tokens for output, resulting in a blended rate of $2.15 per million tokens. Benchmark results for the model include a GPQA score of 0.917, an HLE score of 0.423, a SciCode score of 0.565, and an LCR score of 0.763333333333333.
Benchmark results
4 tracked benchmark rows for GLM-5.3 (max).
GPQA Reasoning
91.7% LCR Other
76.3% SciCode Other
56.5% HLE Other
42.3%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!