FINAL-Bench/Darwin-397B-ZTC

Link successor Darwin-180B-RSI (#1 GPQA Diamond)

Add measurement date and full protocol to GPQA Diamond result

Drop derivative-signal tags (quantized/fp8/w8a8/compressed-tensors); FP8 remains stated in the card body

정정: 폐기값(0.7364/0.7282) → 정본(0.7272/0.7289) + 정정 고지 추가

card: limitation — score shifts when the answering-model mixture changes (measured)

card: generate candidates and let the verifier pick (+2.31 pp); majority voting measured as a loss

card: JEV-compatible API, calibration, and what to do on a low score

eval_results: normalise trailing whitespace and add final newline

card: independent leaderboard 0.7364, per-domain vs baseline, protocol separation

docs: cross-link ZTC ecosystem badges

docs: cross-link ZTC ecosystem badges

Update .eval_results/gpqa_diamond.yaml

Update .eval_results/gpqa_diamond.yaml

re-add GPQA Diamond eval result (93.43, no date field)

reset eval_results to clear stale date index

Add GPQA Diamond eval result (93.43, greedy)

Remove stale eval result file

card: explicit lineage table crediting Qwen/Qwen3.5-397B-A17B

card: attribution moved to body (matches Darwin family convention); base model credited in lineage table and citation

card: drop base_model_relation (this is a Darwin V9 model, not a quantization of the base)

card: document the shipped ZTC probe

ZTC usage example

ZTC probe for Darwin-397B-ZTC (45KB)

eval: GPQA Diamond 93.43 (greedy)

Darwin-397B-ZTC: FP8 397B MoE with Zero-Token Confidence (GPQA Diamond 93.43)

VERITAS 부착: 답+마지막층 은닉 동시 반환 핸들러

VERITAS 부착: 답+마지막층 은닉 동시 반환 핸들러

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

initial commit