Claude Sonnet 4.6 vs GLM 5.2
GLM 5.2 edges ahead on overall intelligence (RunFree 86.3 vs 66.2). Here's how they stack up on benchmarks, price and specs.
Claude Sonnet 4.6
Anthropic
GLM 5.2
Z.ai
Shared benchmarks (3)
Loading chart…
| Claude Sonnet 4.6 | GLM 5.2 | |
|---|---|---|
| RunFree Score | 66.2 | 86.3 |
| Blended price / 1M | $6.00 | $1.46 |
| Input / 1M | $3.00 | $0.95 |
| Output / 1M | $15.00 | $3.00 |
| Context window | 1M | 1.0M |
| Max output | 128K | 33K |
| Reasoning model | Yes | Yes |
| GPQA Diamond | 89.9% | 91.2% |
| Humanity's Last Exam | 33.2% | 40.5% |
| Terminal-Bench | 59.1% | 81% |
| Wins | 1 | 8 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: Claude Sonnet 4.6 card · GLM 5.2 card · full leaderboard