LLM Digest

Model Release Radar

Price/capability frontier position, benchmark scores, and community signal

View as JSON

Model Release Radar

GLM-5.3

zai·open weights·MIT·released Tuesday, Aug 18, 2026

Token prices

USD per million tokens via OpenRouter, Z.AI (z-ai/fp8). Checked 2026-10-17 04:40 UTC.

Cache-write rates with a verified basis replace the ordinary input charge. Unknown rates are never treated as zero.

Frontier position

Behind frontier AA coding index (blended per-1M-token price, 3:1 input/output; not a measured per-task cost) - Muse Spark 1.3, Gemini 3.8 Flash, Gemini 3.7 Flash are priced the same or lower and at least as capable.
Behind frontier AA intelligence index (blended per-1M-token price, 3:1 input/output; not a measured per-task cost) - Muse Spark 1.3, Muse Spark 1.2, Muse Spark Open, Gemini 3.8 Flash, Gemini 3.7 Flash are priced the same or lower and at least as capable.
Behind frontier DeepSWE pass@1 (agentic coding) (measured USD per task) - GPT-5.6 Sol, Gemini 3.8 Flash are priced the same or lower and at least as capable.

Cost vs. capability

Loading chart…

Benchmark scores

Benchmark	Pass@1	Measured cost / task	Frontier
DeepSWE (agentic coding) (max effort, 95% CI 65.9%-72.0%, 4 runs)	69.0%	$3.99 (median $3.13)	behind

Artificial Analysis scores describe capability. Compare them against estimated token spend with your cache mix; these estimates are not measured task costs.

Benchmark	Score
AA intelligence index	44.8
AA coding index	74.8

Variants

This page covers 2 reasoning-effort variants of the same model.

Variant	AA coding index	AA intelligence index	Blended /1M (3:1 input/output)
Max effort (shown above)	74.8	44.8	$2.15/1M
Low effort	-	34.3	$2.15/1M

Community signal

Variant	Coding Elo	Overall Elo	Votes
Max effort	1,495	1,471	22,543