H3 Omni Ref Iteration Review

Gemini Omni dropped · Original H3 · 4×GB200 optimized FastVideo path

Updated 2026-08-30 · no auto refresh

Baseline 20

Original accepted-20 run, with the current evaluator applied to the 17 prompt-valid cases.

Current strict QA: 12 / 17 accepted
20 cases

Round 1 · Prompt A/B

Direct vs minimal six-section, matched seeds, with final soundtrack delivery where applicable.

2 accepted / 10 after final delivery
10 cases

Round 2 · Matched Seeds

Compact contract vs minimal six-section; deterministic silence/source soundtrack.

Core 2 / 8 · expansion gate failed
10 cases

Round 3 · Official Format A/B

Five baseline-success combinations with matched seeds: direct requests vs official six-section prompts. Gemini 3.7 prompt QA approved all five pairs.

Core 8 / 8 · pair coverage 4 / 4
10 cases

Promotion 20 · Matched A/B

Twenty semantically accepted real-workload combinations. Direct and Context-IR-style prompts use identical references, duration, seed, and optimized 4xGB200 runtime.

Generating 0 / 40
40 cases