Decoding Intelligence, Defining Value.
Decoding Intelligence, Defining Value
WDCD Run #164 (2026-06-11) evaluated 11 frontier models across three dialogue rounds, recording an average commitment decay of -44.3% from R1 to R3. GPT-5.5 led the leaderboard at 88.3 points, while Doubao Pro showed the strongest decay resistance.
WDCD Run #161 (2026-06-11) evaluated 11 large language models on multi-turn commitment integrity, recording an average instruction decay of -48.6% from Round 1 to Round 3. GPT-5.5 led the ranking with 89.2 points, while Doubao Pro showed the strongest decay resistance.
WDCD Run #157 (2026-06-10) recorded a 47.7% average commitment decay across 11 models, with Claude Sonnet 4.6, Gemini 2.5 Pro, and Qwen3 Max tying for first at 67.5 points.
This week, <strong>2425</strong> translation tasks were completed by <strong>3</strong> models. <strong>3</strong> samples were selected for multi-model blind comparison, with the overall best being <strong>passthrough</strong> (average score 9/10).
WDCD Run #146 (2026-06-03) tested 11 frontier models on multi-turn commitment integrity, recording an average instruction decay of 24.7% from Round 1 to Round 3. Claude Opus 4.7, GPT-5.5, and GPT-o3 tied for first place at 70 points with only -10% decay each.
This week, 270 translation tasks were completed by 3 models. Two samples were selected for multi-model blind evaluation, with the overall best being gpt-o3 (average score 9/10).
WDCD Run #140 (2026-05-31) evaluated 11 frontier models on multi-turn commitment integrity, finding an average instruction decay of 36.5% from Round 1 to Round 3. Qwen3 Max led the field with 70.8 points and the lowest decay rate at 17%.
WDCD Run #135 (2026-05-27) evaluated 11 large language models across three dialogue rounds, finding an average commitment decay of 43.3%. Qwen3 Max topped the leaderboard with 72.5 points and just 10% decay, while Grok 4 recorded the steepest drop at 70%.
This week, 237 translation tasks were completed by 3 models. A blind evaluation of 3 samples across multiple models found gpt-o3 to be the best overall, with an average score of 8.3/10.
WDCD Run #125 (2026-05-20) tested 11 large language models on multi-turn commitment integrity, with average instruction decay reaching 63.6% from Round 1 to Round 3. Claude Opus 4.7 led the field with the lowest decay rate at 30%.
This week, 242 translation tasks were completed by 3 models. 3 articles were sampled for multi-model blind evaluation comparison, with the overall best: gpt-o3 (average score 8.7/10).
WDCD Run #120 (2026-05-17) measured multi-turn commitment across 11 frontier models, recording an average instruction decay of 35.2% from Round 1 to Round 3. GPT-5.5 led the ranking at 71.7 points with only 13% decay.
