Z.aiopen weightsReasoning
GLM-5.2
99.2% on AIME 2026, the highest reported.
Jun 17, 2026
$1.4 / $4.4
$2.15
1M
Benchmark scores
| Benchmark | Score | Δ vs prior | Rank (current) | Configuration | Source |
|---|---|---|---|---|---|
Terminal-Bench 2.1 | 67.8% | #13 of 21 | Vals run; vendor reports 81.0 · leaderboard | benchlm.ai ↗ | |
GPQA Diamond | 91.2% | #6 of 11 | leaderboard | benchlm.ai ↗ | |
Humanity's Last Exam | 54.7% | #6 of 15 | leaderboard | benchlm.ai ↗ | |
AIME 2026 | 99.2% | #1 of 2 | leaderboard | benchlm.ai ↗ | |
τ²-bench (Telecom) | 99.1% | #1 of 10 | leaderboard | benchlm.ai ↗ | |
Artificial Analysis Intelligence Index | 51.1 | #2 of 11 | leaderboard | benchlm.ai ↗ |