zai-org/GLM-5
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| AIME 2026 | math | 92.7 | AIME 2026 I | medium | | AIME 2026 I | 92.7 | 92.9 | 92.7 | 92.5 | 93.3 | 90.6 | - | |
| GPQA Diamond | reasoning | 86.0 | GPQA-Diamond | medium | | GPQA-Diamond | 86.0 | 85.7 | 82.4 | 87.6 | 87.0 | 91.9 | 92.4 | |
| SWE-bench Verified | swe | 77.8 | SWE-bench Verified | medium | | SWE-bench Verified | 77.8 | 73.8 | 73.1 | 76.8 | 80.9 | 76.2 | 80.0 | |
| BrowseComp | agentic | 75.9 | BrowseComp (w/ Context Manage) | medium | | BrowseComp (w/ Context Manage) | 75.9 | 67.5 | 67.6 | 74.9 | 67.8 | 59.2 | 65.8 | |
| BrowseComp | agentic | 72.7 | BrowseComp-Zh | medium | | BrowseComp-Zh | 72.7 | 66.6 | 65.0 | 62.3 | 62.4 | 66.8 | 76.1 | |
| BrowseComp | agentic | 62.0 | BrowseComp | medium | | BrowseComp | 62.0 | 52.0 | 51.4 | 60.6 | 37.0 | 37.8 | - | |
| Humanity's Last Exam | knowledge | 50.4 | HLE (w/ Tools) | medium | | HLE (w/ Tools) | 50.4 | 42.8 | 40.8 | 51.8 | 43.4* | 45.8* | 45.5* | |
| Terminal-Bench 2.0 | agentic-coding | 41.0 | Terminal-Bench 2.0 (Terminus 2) | medium | | Terminal-Bench 2.0 (Terminus 2) | 56.2 / 60.7 † | 41.0 | 39.3 | 50.8 | 59.3 | 54.2 | 54.0 | |
| Terminal-Bench 2.0 | agentic-coding | 32.8 | Terminal-Bench 2.0 (Claude Code) | medium | | Terminal-Bench 2.0 (Claude Code) | 56.2 / 61.1 † | 32.8 | 46.4 | - | 57.9 | - | - | |
| Humanity's Last Exam | knowledge | 30.5 | HLE | medium | | HLE | 30.5 | 24.8 | 25.1 | 31.5 | 28.4 | 37.2 | 35.4 | |
| Terminal-Bench | agentic-coding | 2.0 | medium | Terminal-Bench 2.0 |
none scraped.