Darwin-27B-ZTC
A decision-specialized large language model released by VIDRAFT, and the predecessor of Darwin-27B-ZTC-v5, focused on structured decision classification tasks.
Timeline (last 90 days)
Darwin-27B-ZTC-v5's predecessor version Darwin-27B-ZTC scored 0.74, and the v5 version achieved an accuracy improvement of +0.07.
On the LocalLLaMA/typed-decisions leaderboard, aplomb-1 and Darwin-27B-ZTC tie for second with scores of 0.74; ProKope-421M-8K scores 0.72, ProKope-421M scores 0.71, and typed-decisions-minilm-l6-specialist scores 0.61.
In 137 head-to-head comparisons on the S1MB benchmark, Darwin-27B-ZTC achieved 137 wins and 97 losses; on the same leaderboard, competitor Perplexity ranked 2nd, Cloudflare ranked 17th, and Meta ranked 27th.
Currently all performance data for VKORE and Darwin-27B-ZTC comes from a single source (a report by AI타임스), lacking independent third-party verification.
All Facts (4)
Darwin-27B-ZTC-v5's predecessor version Darwin-27B-ZTC scored 0.74, and the v5 version achieved an accuracy improvement of +0.07.
50%UnverifiedOn the LocalLLaMA/typed-decisions leaderboard, aplomb-1 and Darwin-27B-ZTC tie for second with scores of 0.74; ProKope-421M-8K scores 0.72, ProKope-421M scores 0.71, and typed-decisions-minilm-l6-specialist scores 0.61.
50%UnverifiedIn 137 head-to-head comparisons on the S1MB benchmark, Darwin-27B-ZTC achieved 137 wins and 97 losses; on the same leaderboard, competitor Perplexity ranked 2nd, Cloudflare ranked 17th, and Meta ranked 27th.
50%UnverifiedCurrently all performance data for VKORE and Darwin-27B-ZTC comes from a single source (a report by AI타임스), lacking independent third-party verification.
50%