GLM 5.2 vs Kimi K2 Thinking
GLM 5.2 edges ahead on overall intelligence (RunFree 86.3 vs 45.2). Here's how they stack up on benchmarks, price and specs.
GLM 5.2
Z.ai
Kimi K2 Thinking
MoonshotAI
Shared benchmarks (3)
Loading chart…
| GLM 5.2 | Kimi K2 Thinking | |
|---|---|---|
| RunFree Score | 86.3 | 45.2 |
| Blended price / 1M | $1.46 | $1.07 |
| Input / 1M | $0.95 | $0.60 |
| Output / 1M | $3.00 | $2.50 |
| Context window | 1.0M | 262K |
| Max output | 33K | 262K |
| Reasoning model | Yes | Yes |
| GPQA Diamond | 91.2% | 84.5% |
| Humanity's Last Exam | 40.5% | 23.9% |
| Terminal-Bench | 81% | 47.1% |
| Wins | 5 | 4 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: GLM 5.2 card · Kimi K2 Thinking card · full leaderboard