| |
|
Model Comparison
| Model | Editorial | Structural | Class | Conf | SETL | Theme | | deepseek/deepseek-v3.2-20251201 | 0.00 | ND | Neutral | 0.20 | — | Content Moderation | | @cf/meta/llama-4-scout-17b-16e-instruct lite | +0.40 | ND | Moderate positive | 0.80 | 0.00 | Content Moderation | | @cf/meta/llama-3.3-70b-instruct-fp8-fast lite | -0.20 | ND | Mild negative | 0.80 | 0.00 | AI generated content | | Section | deepseek/deepseek-v3.2-20251201 | @cf/meta/llama-4-scout-17b-16e-instruct lite | @cf/meta/llama-3.3-70b-instruct-fp8-fast lite | | Preamble | 0.00 | ND | ND | | Article 1 | 0.00 | ND | ND | | Article 2 | 0.00 | ND | ND | | Article 3 | 0.00 | ND | ND | | Article 4 | 0.00 | ND | ND | | Article 5 | 0.00 | ND | ND | | Article 6 | 0.00 | ND | ND | | Article 7 | 0.00 | ND | ND | | Article 8 | 0.00 | ND | ND | | Article 9 | 0.00 | ND | ND | | Article 10 | 0.00 | ND | ND | | Article 11 | 0.00 | ND | ND | | Article 12 | 0.00 | ND | ND | | Article 13 | 0.00 | ND | ND | | Article 14 | 0.00 | ND | ND | | Article 15 | 0.00 | ND | ND | | Article 16 | 0.00 | ND | ND | | Article 17 | 0.00 | ND | ND | | Article 18 | 0.00 | ND | ND | | Article 19 | 0.00 | ND | ND | | Article 20 | 0.00 | ND | ND | | Article 21 | 0.00 | ND | ND | | Article 22 | 0.00 | ND | ND | | Article 23 | 0.00 | ND | ND | | Article 24 | 0.00 | ND | ND | | Article 25 | 0.00 | ND | ND | | Article 26 | 0.00 | ND | ND | | Article 27 | 0.00 | ND | ND | | Article 28 | 0.00 | ND | ND | | Article 29 | 0.00 | ND | ND | | Article 30 | 0.00 | ND | ND | | Summary ~lite Content Moderation Acknowledges Proposal to add AI-generated content flag reason
Lite evaluation by llama-4-scout-wai · editorial channel only · no per-section breakdown available
| |
Longitudinal
· 3 evals | |
Audit Trail
10 entries | 2026-03-01 03:51 | eval_success | Evaluated: Neutral (0.00) | - - | | 2026-03-01 03:51 | model_divergence | Cross-model spread 0.60 exceeds threshold (3 models) | - - | | 2026-03-01 03:51 |
eval
|
Evaluated by deepseek-v3.2: 0.00 (Neutral) 10,963 tokens | | | 2026-02-28 06:07 | model_divergence | Cross-model spread 0.60 exceeds threshold (2 models) | - - | | 2026-02-28 06:07 | eval_success | Light evaluated: Moderate positive (0.40) | - - | | 2026-02-28 06:07 |
eval
|
Evaluated by llama-4-scout-wai: +0.40 (Moderate positive) | | | reasoning Editorial discussion on AI-generated content moderation | | 2026-02-28 06:07 | rater_validation_warn | Light validation warnings for model llama-4-scout-wai: 0W 1R | - - | | 2026-02-28 05:57 | eval_success | Light evaluated: Mild negative (-0.20) | - - | | 2026-02-28 05:57 | rater_validation_warn | Light validation warnings for model llama-3.3-70b-wai: 0W 1R | - - | | 2026-02-28 05:57 |
eval
|
Evaluated by llama-3.3-70b-wai: -0.20 (Mild negative) | | | |
| |