GLM-5 versus Kimi K3

What are we comparing?

This comparison pits two open-weight models that you can install on your own servers against each other: GLM-5 and Kimi K3, one from Zhipu AI (Z.ai), the other from Moonshot AI. The first dates from February 12, 2026, the second from July 16, 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.

Which one is more capable?

On our capability index, GLM-5 scores 77.2 out of 100 and Kimi K3 80.7. Kimi K3 leads by 3.5 points.

On the 2 benchmarks reported for both, GLM-5 wins 0 times and Kimi K3 2:

• GPQA Diamond (PhD-level science questions): GLM-5 87.8%, Kimi K3 93.1%
• OTIS Mock AIME (competition mathematics problems): GLM-5 80%, Kimi K3 97.2%

Budget

GLM-5 costs $0.60 per million input tokens and $2.69 per million output tokens; Kimi K3 costs $3 and $15.

For a typical agent task (read 20,000 tokens, write 2,000), expect $0.017 with GLM-5 versus $0.09 with Kimi K3. GLM-5 is 5.2 times cheaper, a gap that adds up quickly over 1,000 tasks: $72.67 difference.

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

Context and capabilities

Kimi K3 reads more in one go: 1,048,576 tokens of context (roughly 1,573 pages), versus 204,800 for GLM-5.

Reasoning mode: GLM-5 yes, Kimi K3 yes. Tool calling: GLM-5 yes, Kimi K3 yes. Image input: GLM-5 no, Kimi K3 yes.

Both publish their weights: you can host them yourself.

In short

Our reading of the data:

• Choose GLM-5 for a lower cost.
• Choose Kimi K3 for a higher capability index, a larger context window, a more recent release and image input.

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