Darwin-27B-ZTC-v5
A decision engine model developed by VIDRAFT, ranked first among 152 models on the public S1MB leaderboard.
Core Facts
Timeline (last 90 days)
Darwin-27B-ZTC-v5's internal architecture or training differences have not yet been publicly disclosed.
Darwin-27B-ZTC-v5 achieved an accuracy score of 0.81 on the LocalLLaMA/typed-decisions benchmark on Hugging Face.
Darwin-27B-ZTC-v5 topped the LocalLLaMA/typed-decisions leaderboard with a score of 0.81, the highest score ever recorded on that leaderboard.
Darwin-27B-ZTC-v5's predecessor version Darwin-27B-ZTC scored 0.74, and the v5 version achieved an accuracy improvement of +0.07.
Darwin-27B-ZTC-v5 has 27 billion parameters.
Darwin-27B-ZTC-v5 took first place on the S1MB Japanese track with a Borda score of 84.57, leading second-place Perplexity (80.86) by 3.71 points.
VIDRAFT's judgment engine model Darwin-27B-ZTC-v5 ranked first among 152 models on the public benchmark S1MB, and the company says its performance exceeds the models of Perplexity, Cloudflare, and Meta.
As of the time of reporting, VKORE, Darwin-27B-ZTC-v5 and the RSI engine were all not publicly available, with no Hugging Face repository, GitHub code repository or public API.
On the public S1MB leaderboard, Darwin-27B-ZTC-v5 ranks first among 152 models.
All Facts (9)
On the public S1MB leaderboard, Darwin-27B-ZTC-v5 ranks first among 152 models.
65%UnverifiedDarwin-27B-ZTC-v5's internal architecture or training differences have not yet been publicly disclosed.
50%UnverifiedDarwin-27B-ZTC-v5 topped the LocalLLaMA/typed-decisions leaderboard with a score of 0.81, the highest score ever recorded on that leaderboard.
50%UnverifiedDarwin-27B-ZTC-v5's predecessor version Darwin-27B-ZTC scored 0.74, and the v5 version achieved an accuracy improvement of +0.07.
50%UnverifiedDarwin-27B-ZTC-v5 has 27 billion parameters.
50%UnverifiedDarwin-27B-ZTC-v5 achieved an accuracy score of 0.81 on the LocalLLaMA/typed-decisions benchmark on Hugging Face.
50%UnverifiedDarwin-27B-ZTC-v5 took first place on the S1MB Japanese track with a Borda score of 84.57, leading second-place Perplexity (80.86) by 3.71 points.
50%UnverifiedVIDRAFT's judgment engine model Darwin-27B-ZTC-v5 ranked first among 152 models on the public benchmark S1MB, and the company says its performance exceeds the models of Perplexity, Cloudflare, and Meta.
50%UnverifiedAs of the time of reporting, VKORE, Darwin-27B-ZTC-v5 and the RSI engine were all not publicly available, with no Hugging Face repository, GitHub code repository or public API.
50%