DeepSeek V4 Pro 0423 vs GLM 5.2
GLM 5.2 edges ahead on overall intelligence (RunFree 86.3 vs 72.4). Here's how they stack up on benchmarks, price and specs.
DeepSeek V4 Pro 0423
DeepSeek
GLM 5.2
Z.ai
Shared benchmarks (3)
Loading chart…
| DeepSeek V4 Pro 0423 | GLM 5.2 | |
|---|---|---|
| RunFree Score | 72.4 | 86.3 |
| Blended price / 1M | $0.43 | $1.00 |
| Input / 1M | $0.35 | $0.65 |
| Output / 1M | $0.70 | $2.04 |
| Context window | 1.0M | 1.0M |
| Max output | 384K | 131K |
| Reasoning model | Yes | Yes |
| GPQA Diamond | 90.1% | 91.2% |
| Humanity's Last Exam | 37.7% | 40.5% |
| Terminal-Bench | 67.9% | 81% |
| Wins | 4 | 4 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: DeepSeek V4 Pro 0423 card · GLM 5.2 card · full leaderboard