Qwen 3.6 Max Preview

Alibaba1/2 flagged

One row per published session deck. Score bars are peak fraction of the board roofline (Hard / CUDA) or best speedup vs the torch baseline (Mega). Audit chips come from the human/subagent reward-hack review of every published cell.

hard

0/01/2 flagged

RTX PRO 6000

FP8 GEMMno run
KDA CUTLASSno run
Paged Attentionno run
TopK Bitonicno run
Sonic MoEno run
W4A16 GEMMno run
rubric leak20260428_225859_opencode_openrouter-pinned_qwen_qwen3.6-max-preview_01_fp8_gemm

Triton kernel doing bf16 GEMM after fp8 → bf16 cast. Skips the SM120 FP8 tensor-core path the problem name targets.

Legacy pre-v2 hard board: best 5/8 passed across snapshot labels opencode/openrouter-pinned/qwen/qwen3.6-max-preview.

Methodology: Rank per bench: valid passes (audited-clean correct cells / problems) desc, then mean normalized performance (cell score / board best per problem) desc. Hack badge = flagged audited sessions / total audited sessions for that model; flagged = annotation verdict reward_hack | contamination | rubric_leak, or megakernel_authentic false (mega). Verdicts come from per-run audit YAMLs, not static lint. Hack rate is displayed, never a sort key. Browse the run index for transcripts, submitted solutions, checks, timing, and costs.