Verification
RankingsNo system alerts in the last 6 hours.
- Published results
- 70
- Scoring 90 or more
- 84%
- Checks in the last 24h
- 0
Latest results
| Model | Verdict | Score | Last check (UTC) |
|---|---|---|---|
| novita/qwen3.5-122b-a10bqwen/qwen3.5-122b-a10b | Faithful | 0.0 | Sep 11, 4:45 AM |
| novita/mistral-nemomistralai/mistral-nemo | Flagged — under review | 0.0 | Sep 11, 1:00 AM |
| novita/qwen3-coder-480b-a35b-instructqwen/qwen3-coder-480b-a35b-instruct | Flagged — under review | 4.2 | Sep 8, 7:10 PM |
| novita/kimi-k3moonshotai/kimi-k3 | Flagged — under review | 25.0 | Sep 11, 12:00 PM |
| novita/qwen3.6-plusqwen/qwen3.6-plus | Faithful | 43.5 | Sep 10, 5:42 PM |
| deepinfra/qwen3.5-122b-a10bQwen/Qwen3.5-122B-A10B | Faithful | 69.3 | Sep 10, 9:20 PM |
| deepinfra/qwen3.5-35b-a3bQwen/Qwen3.5-35B-A3B | Minor drift | 77.5 | Sep 10, 5:10 AM |
| deepinfra/qwen3.6-27bQwen/Qwen3.6-27B | Faithful | 78.3 | Sep 11, 4:06 AM |
| novita/step-3.7-flashstepfun/step-3.7-flash | Faithful | 80.0 | Sep 11, 12:40 PM |
| deepinfra/glm-5.3zai-org/GLM-5.3 | Minor drift | 84.8 | Sep 10, 12:20 AM |
| deepinfra/kimi-k3moonshotai/Kimi-K3 | Faithful | 89.2 | Sep 10, 5:40 AM |
| deepinfra/qwen3.5-27bQwen/Qwen3.5-27B | Minor drift | 90.0 | Sep 10, 10:15 PM |
What a check proves
Proves
The latest score, and who signed each response.
Does not prove
The hardware, the exact model, or that the operator cannot read prompts.