Add evaluation results
#4
by SaylorTwift HF Staff - opened
.eval_results/openPangu-2.0-Flash.yaml
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: MathArena/aime_2026
|
| 3 |
+
task_id: MathArena/aime_2026
|
| 4 |
+
value: 93.3
|
| 5 |
+
date: "2026-07-01"
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 8 |
+
name: "openPangu-2.0-Flash model card"
|
| 9 |
+
notes: "Thinking"
|
| 10 |
+
|
| 11 |
+
- dataset:
|
| 12 |
+
id: MathArena/aime_2026
|
| 13 |
+
task_id: MathArena/aime_2026
|
| 14 |
+
value: 86.5
|
| 15 |
+
date: "2026-07-01"
|
| 16 |
+
source:
|
| 17 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 18 |
+
name: "openPangu-2.0-Flash model card"
|
| 19 |
+
notes: "Non-Thinking"
|
| 20 |
+
|
| 21 |
+
- dataset:
|
| 22 |
+
id: Idavidrein/gpqa
|
| 23 |
+
task_id: diamond
|
| 24 |
+
value: 83.7
|
| 25 |
+
date: "2026-07-01"
|
| 26 |
+
source:
|
| 27 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 28 |
+
name: "openPangu-2.0-Flash model card"
|
| 29 |
+
notes: "Avg@4, Thinking"
|
| 30 |
+
|
| 31 |
+
- dataset:
|
| 32 |
+
id: Idavidrein/gpqa
|
| 33 |
+
task_id: diamond
|
| 34 |
+
value: 79.8
|
| 35 |
+
date: "2026-07-01"
|
| 36 |
+
source:
|
| 37 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 38 |
+
name: "openPangu-2.0-Flash model card"
|
| 39 |
+
notes: "Avg@4, Non-Thinking"
|
| 40 |
+
|
| 41 |
+
- dataset:
|
| 42 |
+
id: claw-eval/Claw-Eval
|
| 43 |
+
task_id: general
|
| 44 |
+
value: 57.7
|
| 45 |
+
date: "2026-07-01"
|
| 46 |
+
source:
|
| 47 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 48 |
+
name: "openPangu-2.0-Flash model card"
|
| 49 |
+
notes: "Pass^3, Thinking"
|
| 50 |
+
|
| 51 |
+
- dataset:
|
| 52 |
+
id: claw-eval/Claw-Eval
|
| 53 |
+
task_id: general
|
| 54 |
+
value: 58.2
|
| 55 |
+
date: "2026-07-01"
|
| 56 |
+
source:
|
| 57 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 58 |
+
name: "openPangu-2.0-Flash model card"
|
| 59 |
+
notes: "Pass^3, Non-Thinking"
|
| 60 |
+
|
| 61 |
+
- dataset:
|
| 62 |
+
id: internlm/WildClawBench
|
| 63 |
+
task_id: overall
|
| 64 |
+
value: 41.5
|
| 65 |
+
date: "2026-07-01"
|
| 66 |
+
source:
|
| 67 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 68 |
+
name: "openPangu-2.0-Flash model card"
|
| 69 |
+
notes: "Avg@3, Thinking"
|
| 70 |
+
|
| 71 |
+
- dataset:
|
| 72 |
+
id: internlm/WildClawBench
|
| 73 |
+
task_id: overall
|
| 74 |
+
value: 35.0
|
| 75 |
+
date: "2026-07-01"
|
| 76 |
+
source:
|
| 77 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 78 |
+
name: "openPangu-2.0-Flash model card"
|
| 79 |
+
notes: "Avg@3, Non-Thinking"
|
| 80 |
+
|
| 81 |
+
- dataset:
|
| 82 |
+
id: SWE-bench/SWE-bench_Verified
|
| 83 |
+
task_id: swe_bench_%_resolved
|
| 84 |
+
value: 63.1
|
| 85 |
+
date: "2026-07-01"
|
| 86 |
+
source:
|
| 87 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 88 |
+
name: "openPangu-2.0-Flash model card"
|
| 89 |
+
notes: "Avg@3, Thinking"
|
| 90 |
+
|
| 91 |
+
- dataset:
|
| 92 |
+
id: SWE-bench/SWE-bench_Verified
|
| 93 |
+
task_id: swe_bench_%_resolved
|
| 94 |
+
value: 57.6
|
| 95 |
+
date: "2026-07-01"
|
| 96 |
+
source:
|
| 97 |
+
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 98 |
+
name: "openPangu-2.0-Flash model card"
|
| 99 |
+
notes: "Avg@3, Non-Thinking"
|