Add Claw-Eval evaluation results

#10
by SaylorTwift HF Staff - opened
Files changed (1) hide show
  1. .eval_results/claw_eval.yaml +30 -0
.eval_results/claw_eval.yaml ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: claw-eval/Claw-Eval
3
+ task_id: general
4
+ value: 62.1
5
+ date: '2026-04-23'
6
+ notes: Pass³% | N=3 | 161 tasks
7
+ source:
8
+ url: https://claw-eval.github.io
9
+ name: Claw-Eval Leaderboard
10
+ user: tobiaslee
11
+ - dataset:
12
+ id: claw-eval/Claw-Eval
13
+ task_id: multimodal
14
+ value: 23.8
15
+ date: '2026-04-23'
16
+ notes: Pass³% | N=3 | 101 tasks
17
+ source:
18
+ url: https://claw-eval.github.io
19
+ name: Claw-Eval Leaderboard
20
+ user: tobiaslee
21
+ - dataset:
22
+ id: claw-eval/Claw-Eval
23
+ task_id: multi_turn
24
+ value: 63.2
25
+ date: '2026-04-23'
26
+ notes: Pass³% | N=3 | 38 tasks
27
+ source:
28
+ url: https://claw-eval.github.io
29
+ name: Claw-Eval Leaderboard
30
+ user: tobiaslee