Model Comparison
Model Editorial Structural Class Conf SETL Theme
@cf/meta/llama-3.3-70b-instruct-fp8-fast lite +0.70 ND Strong positive 0.90 0.00 Wrongful Conviction
@cf/meta/llama-4-scout-17b-16e-instruct lite +0.60 ND Strong positive 0.90 0.00 Wrongful Conviction
Section @cf/meta/llama-3.3-70b-instruct-fp8-fast lite @cf/meta/llama-4-scout-17b-16e-instruct lite Delta
Preamble ND ND
Article 1 ND ND
Article 2 ND ND
Article 3 ND ND
Article 4 ND ND
Article 5 ND ND
Article 6 ND ND
Article 7 ND ND
Article 8 ND ND
Article 9 ND ND
Article 10 ND ND
Article 11 ND ND
Article 12 ND ND
Article 13 ND ND
Article 14 ND ND
Article 15 ND ND
Article 16 ND ND
Article 17 ND ND
Article 18 ND ND
Article 19 ND ND
Article 20 ND ND
Article 21 ND ND
Article 22 ND ND
Article 23 ND ND
Article 24 ND ND
Article 25 ND ND
Article 26 ND ND
Article 27 ND ND
Article 28 ND ND
Article 29 ND ND
Article 30 ND ND
+0.70 Standing by Their Convictions (features.propublica.org)
50 points by danso 2775 days ago | 15 comments on HN | Strong positive ~lite vlite-1.4
Summary ~lite Wrongful Conviction Advocates
Exposing police misconduct
EQ 0.80
SO 0.70
TD 0.60
Lite evaluation by llama-3.3-70b-wai · editorial channel only · no per-section breakdown available
Longitudinal · 7 evals
+1 0 −1 HN
Audit Trail 18 entries
2026-03-01 18:12 eval_success Lite evaluated: Strong positive (0.70) - -
2026-03-01 18:12 eval Evaluated by llama-3.3-70b-wai: +0.70 (Strong positive) 0.00
reasoning
Investigative journalism exposing abuses
2026-03-01 17:14 eval_success Lite evaluated: Strong positive (0.60) - -
2026-03-01 17:14 eval Evaluated by llama-4-scout-wai: +0.60 (Strong positive) 0.00
reasoning
Investigative journalism exposing police misconduct and wrongful conviction
2026-03-01 17:09 eval_success Lite evaluated: Strong positive (0.60) - -
2026-03-01 17:09 eval Evaluated by llama-4-scout-wai: +0.60 (Strong positive) 0.00
reasoning
Investigative journalism exposing police misconduct and wrongful conviction
2026-03-01 16:56 eval_success Lite evaluated: Strong positive (0.70) - -
2026-03-01 16:56 eval Evaluated by llama-3.3-70b-wai: +0.70 (Strong positive) 0.00
reasoning
Investigative journalism exposing abuses
2026-02-28 15:51 credit_exhausted Credit balance too low, pausing provider for 30 min - -
2026-02-28 12:45 eval_success Lite evaluated: Strong positive (0.70) - -
2026-02-28 12:45 eval Evaluated by llama-3.3-70b-wai: +0.70 (Strong positive) 0.00
reasoning
Investigative journalism exposing abuses
2026-02-28 12:45 rater_validation_warn Lite validation warnings for model llama-3.3-70b-wai: 0W 1R - -
2026-02-28 12:40 eval_success Lite evaluated: Strong positive (0.70) - -
2026-02-28 12:40 eval Evaluated by llama-3.3-70b-wai: +0.70 (Strong positive)
reasoning
Investigative journalism exposing abuses
2026-02-28 12:40 rater_validation_warn Lite validation warnings for model llama-3.3-70b-wai: 0W 1R - -
2026-02-28 12:36 eval_success Lite evaluated: Strong positive (0.60) - -
2026-02-28 12:36 eval Evaluated by llama-4-scout-wai: +0.60 (Strong positive)
reasoning
Investigative journalism exposing police misconduct and wrongful conviction
2026-02-28 12:36 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 0W 1R - -