Models
For each AI model version: the capability levels its provider states it reached, the outside testers who tested it, and the incidents that name it.
Also: compare models side by side · statements that a capability level was crossed · providers · practices providers document · safety news.
78 of 78 model versions
| Model | Levels the provider states it reached | Outside testers | Incidents naming it |
|---|---|---|---|
| Claude Sonnet 3.7 Anthropic |
None stated | CAISI (NIST), METR, RAND (CAST / Project Canary), UK AI Security Institute | None |
| Operator OpenAI · 23 January 2025 |
None stated | None named | None |
| DeepSeek-R1 DeepSeek |
None stated | METR | None |
Previous · Page 4 of 4