GLM-5 vs GLM-5.1

Two models head to head

GLM-5 and GLM-5.1 are two open-weight models that you can install on your own servers, both built by Zhipu AI (Z.ai). GLM-5 was released on February 12, 2026, GLM-5.1 on April 7, 2026.

All figures below come from public sources checked on October 22, 2026: models.dev and OpenRouter for prices and capabilities, Epoch AI for scores.

What the benchmarks say

On our capability index, GLM-5 scores 77.2 out of 100 and GLM-5.1 70.9. GLM-5 leads by 6.3 points.

On the 3 benchmarks reported for both, GLM-5 wins 0 times and GLM-5.1 3:

• GPQA Diamond (PhD-level science questions): GLM-5 87.8%, GLM-5.1 89.9%
• OTIS Mock AIME (competition mathematics problems): GLM-5 80%, GLM-5.1 93.3%
• SWE-bench Verified (fixing real software bugs): GLM-5 72.1%, GLM-5.1 74.2%

Budget

GLM-5 costs $0.60 per million input tokens and $2.69 per million output tokens; GLM-5.1 costs $0.90 and $3.59.

For a typical agent task (read 20,000 tokens, write 2,000), expect $0.017 with GLM-5 versus $0.025 with GLM-5.1. GLM-5 is 1.4 times cheaper, a gap that adds up quickly over 1,000 tasks: $7.77 difference.

Run the numbers with your own volumes in the agent cost calculator.

Features and limits

GLM-5 reads more in one go: 204,800 tokens of context (roughly 307 pages), versus 200,000 for GLM-5.1.

Reasoning mode: GLM-5 yes, GLM-5.1 yes. Tool calling: GLM-5 yes, GLM-5.1 yes. Image input: GLM-5 no, GLM-5.1 no.

Both publish their weights: you can host them yourself.

In short

Our reading of the data:

• Choose GLM-5 for a higher capability index and a lower cost.
• Choose GLM-5.1 for a more recent release.

This verdict relies on public figures; it does not replace a trial on your own tasks.