Add evaluation results for HLE, MMLU-Pro
Browse files## Evaluation Results
This PR adds evaluation results extracted from the Model Card.
**Benchmarks:**
- MMLU-Pro: 87.8
- HLE: 28.7
- HLE: 48.3
**Files created:**
- .eval_results/mmlu_pro.yaml
- .eval_results/hle.yaml
- .eval_results/hle_with_tools.yaml
---
Extracted automatically using the [LLM-powered evaluation extractor](https://github.com/huggingface/community-evals).
- .eval_results/hle.yaml +9 -0
- .eval_results/hle_with_tools.yaml +10 -0
- .eval_results/mmlu_pro.yaml +9 -0
.eval_results/hle.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: cais/hle
|
| 3 |
+
task_id: hle
|
| 4 |
+
value: 28.7
|
| 5 |
+
date: '2026-02-16'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/Qwen/Qwen3.5-397B-A17B
|
| 8 |
+
name: Model Card
|
| 9 |
+
user: SaylorTwift
|
.eval_results/hle_with_tools.yaml
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: cais/hle
|
| 3 |
+
task_id: hle
|
| 4 |
+
value: 48.3
|
| 5 |
+
date: '2026-02-16'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/Qwen/Qwen3.5-397B-A17B
|
| 8 |
+
name: Model Card
|
| 9 |
+
user: SaylorTwift
|
| 10 |
+
notes: with tools
|
.eval_results/mmlu_pro.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: TIGER-Lab/MMLU-Pro
|
| 3 |
+
task_id: mmlu_pro
|
| 4 |
+
value: 87.8
|
| 5 |
+
date: '2026-02-16'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/Qwen/Qwen3.5-397B-A17B
|
| 8 |
+
name: Model Card
|
| 9 |
+
user: SaylorTwift
|