GLM 5.2 TEE
GLM-5.2 is Z.AI's flagship model for long-horizon tasks and autonomous workflows, with a 1M-token context window. Running inside a TEE (Trusted Execution Environment), with attestation support.
- Reasoning
- Tool Calling
- Structured Output
Added Jun 16, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $1.25
- Output
- $3.95
- Cache read
- $0.125
Specifications
- Context window
- 1M
- Max output
- 131.1K
- Parameters
- 744B / 40B
- Total / active
Benchmarks
Benchmarks
Leaderboard results
These leaderboards tested GLM 5.2, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 15, 2026 | ||
Epoch Capabilities Index | 153.0 | #51 of 115 |
FrontierMath v2 (Tiers 1–3) | 59.2% | #43 of 83 |
SWE-bench Verified | 78.7% | #4 of 28 |
GPQA Diamond | 91.9% | #27 of 119 |
SimpleQA Verified | 34.2% | #58 of 82 |
FrontierMath v2 (Tier 4) | 29.3% | #36 of 67 |
OTIS Mock AIME 2024–2025 | 86.4% | #71 of 121 |
MirrorCode | 36.7% | #27 of 39 |
Chess Puzzles | 22.0% | #57 of 82 |
Mystery Game Puzzles | 19.0% | #51 of 77 |
Sierra τ-bench tau2-bench data, MIT · Updated Aug 4, 2026 | ||
τ³-Banking | 37.1% | #10 of 18 |
EQ-Bench 4 | 1208 | #18 of 31 |
Creative Writing v3 | 1759 | #29 of 96 |
Longform Writing | 77.9 | #24 of 97 |
EQ-Bench 3 | 1563 | #6 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 58.9 | #9 of 149 |
UGI Willingness | 2.8 | #82 of 149 |
UGI Writing | 67.0 | #19 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $1.25 | $3.95 | $0.125 | N/A | N/A | |
| $1.25 | $3.95 | $0.125 | N/A | N/A | |
| $1.31 | $4.15 | $0.131 | N/A | N/A | |
| $1.32 | $3.15 | $0.231 | N/A | N/A |