AA-Briefcase
1.1 / combined Elo ↗- GLM-5.3:
- Kimi K3.1 Pro:
GLM-5.3 vs Kimi K3.1 Pro
Find the right model, side by side.
Across 7 shared evaluation tracks, GLM-5.3 leads on 0, Kimi K3.1 Pro leads on 7, and 0 are tied. These counts describe reported scores within matched setups, not an overall model ranking. At the initially selected providers, input/output prices are $1.40 / $4.40 for GLM-5.3 and $2.00 / $10.00 for Kimi K3.1 Pro, per million tokens.
Updated: Data as of:
First model
Second model
Model specifications
| Specifications |  GLM-5.3Z.ai |  Kimi K3.1 ProMoonshot AI |
|---|---|---|
| Provider | ||
| Context sizetokens | 1,000,000 | 1,000,000 |
| Cutoff date | Not reported | Not reported |
| Input costUSD / 1M tokens | $1.40 | $2.00 |
| Output costUSD / 1M tokens | $4.40 | $10.00 |
| Max outputtokens | 131,072 | 1,048,576 |
| LatencyTTFT · seconds | 1.477 | 3.427 |
| Speedtokens / sec | 88.436 | 31.249 |
Benchmark performance
7 shared benchmark comparisons. Versions and setups matched.
GLM-5.3Kimi K3.1 Pro
AutomationBench-AA
1.0.6 / AA private 657 ↗Tools enabled- GLM-5.3:
- Kimi K3.1 Pro:
- GLM-5.3:
- Kimi K3.1 Pro:
GDPval-AA
2.1 ↗- GLM-5.3:
- Kimi K3.1 Pro:
HLE-Diamond
1,000 questions / no tools ↗No tools- GLM-5.3:
- Kimi K3.1 Pro:
Humanity’s Last Exam
Stable HLE — text-only subset ↗No tools · 2158 questions- GLM-5.3:
- Kimi K3.1 Pro:
Terminal-Bench
4.0 / mini-swe-agent ↗mini-swe-agent- GLM-5.3:
- Kimi K3.1 Pro:
