Sync Quality Benchmark from reviewed MR !13060

Sync only the complete Quality Benchmark section from GitLab MR !13060 at eddc7e7a1f221b6f31ec6c107e32e91d8fc31bea. Preserve all other README sections and repository files unchanged.

README.md

@@ -239,7 +239,7 @@ For more information about the datasets used to train this model, please see the
 
 ### Reasoner Benchmarks
 
-We compare **Cosmos3-Edge-FP8** with its BF16 counterpart across general reasoning, robotics, smart infrastructure, and driving benchmarks. Each domain score is the unweighted mean of the included benchmark scores. The benchmark list below defines the evaluation scope. Benchmarks without FP8 results are excluded.
+We compare **Cosmos3-Edge-FP8** with its BF16 counterpart across general reasoning, robotics, smart infrastructure, and driving benchmarks. Each domain score is the unweighted mean of the benchmark scores listed below, using the same benchmark set for BF16 and FP8.
 
 | Domain | BF16 | FP8 |
 | --- | --- | --- |
@@ -255,16 +255,16 @@ We compare **Cosmos3-Edge-FP8** with its BF16 counterpart across general reasoni
 
 ### Generator Benchmarks
 
-We compare **Cosmos3-Edge-FP8** with its BF16 counterpart. PAIBench-G evaluates text-to-video and image-to-video generation. RBench assesses task correctness, physical plausibility, and visual fidelity in robotics videos. PhysicsIQ compares video continuations with recorded physical outcomes.
+We compare **Cosmos3-Edge-FP8** with its BF16 counterpart. PAIBench-G evaluates text-to-video and image-to-video generation. RBench assesses task correctness, physical plausibility, and visual fidelity in robotics videos. PhysicsIQ evaluates image-to-video generation by comparing predicted video continuations with recorded physical outcomes.
 
 | Benchmark | BF16 | FP8 |
 | --- | --- | --- |
 | PAIBench-G I2V ↑ | 81.10 | 80.75 |
 | PAIBench-G T2V ↑ | 76.90 | 76.58 |
-| RBench ↑ | 55.10 | 56.52 |
-| PhysicsIQ ↑ | 31.28 | 31.37 |
+| RBench ↑ | 0.55 | 0.57 |
+| PhysicsIQ I2V ↑ | 31.28 | 31.37 |
 
-*For quality benchmarks, BF16 results were obtained using PyTorch. FP8 results were obtained using vLLM-Omni.*
+*For quality benchmarks, BF16 results were obtained using PyTorch, and FP8 results were obtained using vLLM-Omni.*
 
 ## Performance Benchmark