GLM 5.3 Flash

The numbers

Open weights — you can run this model yourself.

Exact source entries: Artificial Analysis “GLM 5.3 Flash”, retrieved 2026-09-19.

Try or learn more

Honest read

Best at

• Intelligence Index 41.9 at $0.15 / $0.50 per million tokens — 176 index points per blended $1M, the best we recorded
• MIT license, open weights
• 1,000,000-token context, ~97 tokens/second median output

Not the pick for

• Not frontier-top on raw quality — Arena Score 1475 puts it outside the overall top 10
• Smaller ecosystem and tooling than the big labs

Choose it if you are

Startups, agents and pipelines paying per token at scale who refuse to give up real capability.

Rankings come from the sources above; this plain-language read is our editorial summary of those numbers.