GLM-5.3 Benchmarks, Pricing & Rankings
Zhipu AI · 2026-08-20 · Open · Current
Snapshot 2026-10-14 · updated weekly
GLM-5.3 ranks #19 of 42 on the AMR leaderboard.
GLM-5.3 benchmark scores
| GPQA Diamond | 85.2% | |
| MMLU-Pro | 82.4% | |
| SWE-Bench Verified | 64.1% | |
| AIME 2025 | 84.8% | |
| LiveCodeBench v6 | 72.6% | |
| Arena Elo | 1391 |
GLM-5.3 price, speed & context
Input price
$0.40
per 1M tokens
Output price
$1.50
per 1M tokens
Speed
118
tok/s
Context
256K
tokens
About GLM-5.3
GLM-5.3 is Zhipu’s open-weights flagship and a favorite self-hosted coding model, with one of the best SWE-Bench scores per parameter in the open tier.
Models around GLM-5.3 in the rankings
More Zhipu AI models
GLM-5.3 FAQ
Where does GLM-5.3 rank?
GLM-5.3 ranks #19 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 85.5. Its strongest dimension is GPQA Diamond at 85.2%.
How much does GLM-5.3 cost?
GLM-5.3 costs $0.40 per million input tokens and $1.50 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $1.23 per million tokens.
What is the GLM-5.3 context window?
GLM-5.3 supports a 256K token context window and generates at a median 118 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is GLM-5.3 open source?
Yes — GLM-5.3 ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than GLM-5.3?
Muse Wonder Full ranks one place higher at #18 with an AMR score of 86.8. GLM-5.3 still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.