Add WBench evaluation results
Browse filesThis PR adds this model's results on [**WBench**](https://github.com/meituan-longcat/WBench) — a multi-turn benchmark for interactive video world models (289 cases, 22 metrics, 5 dimensions), now registered as a benchmark on the Hub.
Scores link to the [leaderboard](https://meituan-longcat.github.io/WBench/). Feel free to close if you'd prefer not to include it — thanks for the great work!
.eval_results/wbench.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: meituan-longcat/WBench
|
| 3 |
+
task_id: wbench_navi
|
| 4 |
+
value: 78.8
|
| 5 |
+
source:
|
| 6 |
+
url: https://meituan-longcat.github.io/WBench/
|
| 7 |
+
name: WBench Leaderboard
|