imlrz commited on
Commit
f9c0202
·
0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +36 -0
  2. .gitignore +10 -0
  3. Dockerfile +15 -0
  4. README.md +28 -0
  5. app.py +17 -0
  6. create_leaderboard.py +199 -0
  7. data/data_viewer.jsonl +3 -0
  8. data/data_viewer_index.json +0 -0
  9. data/fact_results/doubao-deepresearch/fact_result.txt +3 -0
  10. data/fact_results/gemini-2.5-pro-deepresearch/fact_result.txt +3 -0
  11. data/fact_results/gensee-search-gpt-5/fact_result.txt +3 -0
  12. data/fact_results/langchain-open-deep-research-gpt-5/fact_result.txt +3 -0
  13. data/fact_results/langchain-open-deep-research/fact_result.txt +3 -0
  14. data/fact_results/openai-deepresearch/fact_result.txt +3 -0
  15. data/fact_results/perplexity-Research/fact_result.txt +3 -0
  16. data/leaderboard.csv +46 -0
  17. data/raw_data/1688AILab-DeepResearch-0325.jsonl +3 -0
  18. data/raw_data/RecallRadar.jsonl +3 -0
  19. data/raw_data/TrajectoryKit.jsonl +3 -0
  20. data/raw_data/baidu-qianfan-drs-pro.jsonl +3 -0
  21. data/raw_data/baidu-qianfan-drs.jsonl +3 -0
  22. data/raw_data/claude-research.jsonl +3 -0
  23. data/raw_data/deepinsight.jsonl +3 -0
  24. data/raw_data/deepsynth.jsonl +3 -0
  25. data/raw_data/doubao-deepresearch.jsonl +3 -0
  26. data/raw_data/dr-tulu.jsonl +3 -0
  27. data/raw_data/drb_cellcog.jsonl +3 -0
  28. data/raw_data/drb_cellcog_max.jsonl +3 -0
  29. data/raw_data/gemini-2.5-pro-deepresearch.jsonl +3 -0
  30. data/raw_data/gensee-search-gpt-5.jsonl +3 -0
  31. data/raw_data/grep-v4.jsonl +3 -0
  32. data/raw_data/kimi-researcher.jsonl +3 -0
  33. data/raw_data/langchain-open-deep-research-gpt-5.jsonl +3 -0
  34. data/raw_data/langchain-open-deep-research.jsonl +3 -0
  35. data/raw_data/ms_deepresearch.jsonl +3 -0
  36. data/raw_data/nvidia-aiq-nemotron-gpt52-updated.jsonl +3 -0
  37. data/raw_data/nvidia-aiq-research-assistant.jsonl +3 -0
  38. data/raw_data/onyx.jsonl +3 -0
  39. data/raw_data/openai-deepresearch.jsonl +3 -0
  40. data/raw_data/perplexity-Research.jsonl +3 -0
  41. data/raw_data/raaa-deep-research.jsonl +3 -0
  42. data/raw_data/salesforce-air-deep-research.jsonl +3 -0
  43. data/raw_data/tavily-research.jsonl +3 -0
  44. data/raw_data/thinkdepthai-deepresearch.jsonl +3 -0
  45. data/raw_data/tongyi-deepresearch-30B-A3B.jsonl +3 -0
  46. data/raw_data/xiaoyi_research_agent_0304.jsonl +3 -0
  47. data/raw_results/1688AILab-DeepResearch-0325/race_result.txt +5 -0
  48. data/raw_results/1688AILab-DeepResearch-0325/raw_results.jsonl +3 -0
  49. data/raw_results/1688AILab-DeepResearch-0428/race_result.txt +5 -0
  50. data/raw_results/1688AILab-DeepResearch-0428/raw_results.jsonl +3 -0
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.jsonl filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ __pycache__/
2
+ *.py[cod]
3
+ *$py.class
4
+ .env
5
+ .venv
6
+ env/
7
+ venv/
8
+ ENV/
9
+ .DS_Store
10
+ *.log# trigger
Dockerfile ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.10-slim
2
+
3
+ WORKDIR /code
4
+
5
+ COPY requirements.txt /code/requirements.txt
6
+ RUN pip install --no-cache-dir --upgrade pip && \
7
+ pip install --no-cache-dir -r requirements.txt
8
+
9
+ COPY . /code/
10
+
11
+ ENV PYTHONUNBUFFERED=1
12
+
13
+ EXPOSE 7860
14
+
15
+ CMD ["python", "-u", "app.py"]
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: DeepResearch Bench
3
+ emoji: 🔍
4
+ colorFrom: blue
5
+ colorTo: indigo
6
+ sdk: docker
7
+ app_file: app.py
8
+ pinned: false
9
+ license: apache-2.0
10
+ ---
11
+
12
+ # DeepResearch Bench Leaderboard
13
+
14
+ A comprehensive benchmark and leaderboard for evaluating Deep Research Agents.
15
+
16
+ ## Overview
17
+ This Hugging Face Space hosts the interactive leaderboard for the DeepResearch Bench project.
18
+
19
+ Visit our [project website](https://deepresearch-bench.github.io) for more information.
20
+
21
+ ### Local Development
22
+ ```bash
23
+ pip install -r requirements.txt
24
+ python app.py
25
+ ```
26
+
27
+ ## Hugging Face Space Details
28
+ - SDK: Docker
app.py ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ DeepResearch Bench HF Space 入口文件
5
+ """
6
+
7
+ from __future__ import annotations
8
+ from create_leaderboard import demo
9
+
10
+
11
+ if __name__ == "__main__":
12
+ demo.launch(
13
+ server_name="0.0.0.0",
14
+ server_port=7860,
15
+ share=False,
16
+ show_api=False,
17
+ )
create_leaderboard.py ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ Gradio UI – v2.1 (Leaderboard · Data Viewer · Prompt-to-Leaderboard)
5
+ """
6
+
7
+ from __future__ import annotations
8
+ from pathlib import Path
9
+ from datetime import datetime
10
+ import pandas as pd
11
+ import gradio as gr
12
+
13
+ # ---- Tab 组件 ----
14
+ from tabs.leaderboard_tab import create_leaderboard_tab
15
+ from tabs.leaderboard_tab_gpt55 import create_leaderboard_tab_gpt55
16
+ from tabs.data_viewer_tab import create_data_viewer_tab
17
+ from tabs.data_viewer_side_by_side_tab import create_data_viewer_side_by_side_tab
18
+
19
+ def get_leaderboard_info():
20
+ leaderboard_path = Path(__file__).parent / "data" / "leaderboard.csv"
21
+ if leaderboard_path.exists():
22
+ try:
23
+ df = pd.read_csv(leaderboard_path)
24
+ model_count = len(df)
25
+ mtime = leaderboard_path.stat().st_mtime
26
+ last_update = datetime.fromtimestamp(mtime).strftime("%d %B %Y")
27
+ return model_count, last_update
28
+ except Exception:
29
+ pass
30
+ return 21, "02 August 2025"
31
+
32
+ model_count, last_update = get_leaderboard_info()
33
+
34
+ # ---------------------------------------------------------------------------
35
+ # UI
36
+ # ---------------------------------------------------------------------------
37
+
38
+ with gr.Blocks(title="DeepResearch Bench") as demo:
39
+
40
+ # ========= 全局 CSS(仅作用于自定义标题 & 简介) =========
41
+ gr.HTML("""
42
+ <style>
43
+ .title-block{
44
+ /* 渐变文字效果 - 改进版 */
45
+ background: linear-gradient(to right, #009CFF, #823AFF);
46
+ background: -webkit-linear-gradient(to right, #009CFF, #823AFF);
47
+ background: -moz-linear-gradient(to right, #009CFF, #823AFF);
48
+ -webkit-background-clip: text;
49
+ -webkit-text-fill-color: transparent;
50
+ background-clip: text;
51
+ color: transparent;
52
+
53
+ text-align: center;
54
+ font-size: 2rem;
55
+ font-weight: 700;
56
+ margin: 0 0 1rem 0;
57
+ padding-bottom: 0.2rem;
58
+ display: inline-block; /* 重要:确保渐变效果正常 */
59
+ width: 100%; /* 确保居中对齐 */
60
+ }
61
+ .intro-block{
62
+ text-align:center;
63
+ margin-bottom:1.25rem;
64
+ line-height:2;
65
+ }
66
+ .intro-block a{
67
+ color:#0a58ca;
68
+ text-decoration:none;
69
+ margin:0 .3rem;
70
+ }
71
+ .intro-block a:hover{ text-decoration:underline; }
72
+ </style>
73
+ """)
74
+
75
+ # ========= 顶部标题 & 简介(不使用 Markdown 标题语法) =========
76
+ gr.HTML(f"""
77
+ <div class="title-block">
78
+ DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
79
+ </div>
80
+
81
+ <div class="intro-block">
82
+ The research aims to comprehensively evaluate the capabilities of Deep Research Agents.<br>
83
+ <a href="https://github.com/Ayanami0730/deep_research_bench" target="_blank">Code</a> |
84
+ <a href="https://deepresearch-bench.github.io" target="_blank">Website</a> |
85
+ <a href="https://arxiv.org/abs/2506.11763" target="_blank">Paper</a> |
86
+ <a href="#" target="_blank">Eval Dataset</a> |
87
+ Total models: {model_count} | Last Update: {last_update}<br>
88
+ <small style="color: #666; font-size: 0.9em;">
89
+ Leaderboard tab — Race judge: GPT-5.5 | Fact-check: GPT-5.4-mini<br>
90
+ Gemini-2.5 Eval tab — Race judge: gemini-2.5-pro | Fact-check: gemini-2.5-flash
91
+ </small>
92
+ </div>
93
+ """)
94
+
95
+ # ========= 主 Tabs =========
96
+ with gr.Tabs():
97
+ create_leaderboard_tab_gpt55() # 🏆 Leaderboard
98
+ create_leaderboard_tab() # 🏆 Leaderboard (Gemini-2.5 Eval)
99
+
100
+ sbs_on_load, sbs_outputs = create_data_viewer_side_by_side_tab()
101
+ dv_on_load, dv_outputs = create_data_viewer_tab()
102
+
103
+ with gr.Tab("💬Prompt-to-Leaderboard"):
104
+ gr.Markdown(
105
+ """
106
+ 🚧 **Prompt-to-Leaderboard** module not implemented yet.
107
+ Planned: inspect how individual prompts affect overall model ranking.
108
+ """
109
+ )
110
+
111
+ demo.load(fn=dv_on_load, outputs=dv_outputs)
112
+ demo.load(fn=sbs_on_load, outputs=sbs_outputs)
113
+
114
+ # ========= Citation 板块 =========
115
+ gr.HTML("""
116
+ <style>
117
+ .citation-block {
118
+ margin-top: 2rem;
119
+ padding: 1.5rem;
120
+ border: 1px solid #e0e0e0;
121
+ border-radius: 8px;
122
+ background-color: #f9f9f9;
123
+ }
124
+ .citation-title {
125
+ font-size: 1.25rem;
126
+ font-weight: 600;
127
+ margin-bottom: 1rem;
128
+ color: #333;
129
+ }
130
+ .citation-content {
131
+ background-color: #fff;
132
+ border: 1px solid #ddd;
133
+ border-radius: 4px;
134
+ padding: 1rem;
135
+ font-family: monospace;
136
+ font-size: 0.9rem;
137
+ white-space: pre-wrap;
138
+ line-height: 1.5;
139
+ position: relative;
140
+ }
141
+ .copy-btn {
142
+ position: absolute;
143
+ top: 8px;
144
+ right: 8px;
145
+ padding: 6px 12px;
146
+ background-color: #0a58ca;
147
+ color: white;
148
+ border: none;
149
+ border-radius: 4px;
150
+ cursor: pointer;
151
+ font-size: 0.85rem;
152
+ transition: background-color 0.2s;
153
+ }
154
+ .copy-btn:hover {
155
+ background-color: #084298;
156
+ }
157
+ .copy-btn.copied {
158
+ background-color: #198754;
159
+ }
160
+ </style>
161
+
162
+ <div class="citation-block">
163
+ <div class="citation-title">📚 Citation</div>
164
+ <div class="citation-content" id="citation-text">
165
+ <button class="copy-btn" onclick="copyCitation()">Copy</button>
166
+ @article{du2025deepresearch,
167
+ author = {Mingxuan Du and Benfeng Xu and Chiwei Zhu and Xiaorui Wang and Zhendong Mao},
168
+ title = {DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents},
169
+ journal = {arXiv preprint},
170
+ year = {2025},
171
+ }</div>
172
+ </div>
173
+
174
+ <script>
175
+ function copyCitation() {
176
+ const citationText = `@article{du2025deepresearch,
177
+ author = {Mingxuan Du and Benfeng Xu and Chiwei Zhu and Xiaorui Wang and Zhendong Mao},
178
+ title = {DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents},
179
+ journal = {arXiv preprint},
180
+ year = {2025},
181
+ }`;
182
+ navigator.clipboard.writeText(citationText).then(function() {
183
+ const btn = document.querySelector('.copy-btn');
184
+ btn.textContent = 'Copied!';
185
+ btn.classList.add('copied');
186
+ setTimeout(function() {
187
+ btn.textContent = 'Copy';
188
+ btn.classList.remove('copied');
189
+ }, 2000);
190
+ });
191
+ }
192
+ </script>
193
+ """)
194
+
195
+ # ---------------------------------------------------------------------------
196
+ # Entrypoint
197
+ # ---------------------------------------------------------------------------
198
+ if __name__ == "__main__":
199
+ demo.launch()
data/data_viewer.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bae4095b938b71ffe6717a24540f0aed93e4fca82c5f27fceb2183a8e5793d0
3
+ size 198715476
data/data_viewer_index.json ADDED
The diff for this file is too large to render. See raw diff
 
data/fact_results/doubao-deepresearch/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ citations_per_task: 99.5510
2
+ supported_per_task: 52.6224
3
+ valid_rate: 0.5286
data/fact_results/gemini-2.5-pro-deepresearch/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ citations_per_task: 211.1616
2
+ supported_per_task: 165.3434
3
+ valid_rate: 0.7830
data/fact_results/gensee-search-gpt-5/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ citations_per_task: 63.9394
2
+ supported_per_task: 21.0606
3
+ valid_rate: 0.3294
data/fact_results/langchain-open-deep-research-gpt-5/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ citations_per_task: 64.6162
2
+ supported_per_task: 22.4444
3
+ valid_rate: 0.3474
data/fact_results/langchain-open-deep-research/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ citations_per_task: 60.0600
2
+ supported_per_task: 29.4900
3
+ valid_rate: 0.4910
data/fact_results/openai-deepresearch/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ total_citations: 53.04040404040404
2
+ total_valid_citations: 39.78787878787879
3
+ valid_rate: 0.7501428299371549
data/fact_results/perplexity-Research/fact_result.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ total_citations: 37.76
2
+ total_valid_citations: 31.2
3
+ valid_rate: 0.826271186440678
data/leaderboard.csv ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,overall_score,comprehensiveness,insight,instruction_following,readability,citation_accuracy,effective_citations
2
+ qianfan_deepresearch_0430,58.03,59.48,61.48,53.87,54.34,-,-
3
+ ZTE-Nebula-DeepResearch-V20260519,57.27,58.37,59.76,54.06,54.66,-,-
4
+ Link,57.08,58.24,59.74,53.24,55.05,-,-
5
+ zhipu_deep_research,57.06,58.15,60.14,53.47,53.88,-,-
6
+ xiaoyi,57.00,58.58,59.38,53.58,53.99,-,-
7
+ WhaleCloud-DocChain,56.81,57.13,59.30,53.98,54.97,-,-
8
+ cellcog-max,56.67,57.40,60.01,53.25,53.21,-,-
9
+ 1688AILab-DeepResearch-0428,56.53,57.32,59.27,53.51,53.36,-,-
10
+ octen-deepresearch-0508,56.31,56.89,59.00,53.39,53.83,-,-
11
+ grep-v5,56.23,56.82,58.92,53.38,53.44,-,-
12
+ nvidia-aiq-nemotron-gpt52-updated,55.95,56.90,58.49,52.89,53.43,-,-
13
+ 1688AILab-DeepResearch-0325,55.39,55.48,57.59,53.38,53.50,-,-
14
+ ms_deepresearch_gpt52mixqwen35_09_edit_restart09_think_medium,55.31,56.76,56.79,53.10,52.28,-,-
15
+ drb_cellcog,55.31,55.41,58.21,52.50,53.12,-,-
16
+ deepinsight,55.24,55.66,58.70,52.53,50.94,-,-
17
+ ms_deepresearch,54.97,56.45,56.22,53.25,51.71,-,-
18
+ TrajectoryKit,54.92,54.10,57.90,52.91,52.72,-,-
19
+ onyx,54.54,54.67,56.43,53.08,52.02,-,-
20
+ deepsynth,54.22,54.23,56.09,52.86,51.81,-,-
21
+ deepdog,53.52,53.14,56.10,51.83,51.18,-,-
22
+ RecallRadar,53.19,53.91,53.53,52.18,52.38,-,-
23
+ MindDR-V1.5,52.54,51.54,55.30,50.45,51.26,-,-
24
+ tavily-research,52.44,52.84,53.59,51.92,49.21,-,-
25
+ thinkdepthai-deepresearch,52.43,52.02,53.88,52.04,50.12,-,-
26
+ salesforce-air-deep-research,50.65,50.00,51.09,50.77,50.32,-,-
27
+ gensee-search-gpt-5,50.60,50.06,50.76,51.31,49.72,32.94,21.06
28
+ gemini-2.5-pro-deepresearch,49.71,49.51,49.45,50.12,50.00,78.30,165.34
29
+ langchain-open-deep-research-gpt-5,49.33,49.80,47.34,51.05,48.99,34.74,22.44
30
+ openai-deepresearch,46.45,46.46,43.73,49.39,47.22,75.01,39.79
31
+ raaa-deep-research,46.13,43.77,48.34,47.21,43.78,-,-
32
+ dr-tulu,45.49,44.08,44.65,49.56,42.30,-,-
33
+ claude-research,45.00,45.34,42.79,47.58,44.66,-,-
34
+ kimi-researcher,44.64,44.96,41.97,47.14,45.59,-,-
35
+ doubao-deepresearch,44.34,44.84,40.56,47.95,44.69,52.86,52.62
36
+ langchain-open-deep-research,43.44,42.97,39.17,48.09,45.22,49.10,29.49
37
+ nvidia-aiq-research-assistant,40.52,37.98,38.39,44.59,42.63,-,-
38
+ tongyi-deepresearch-30B-A3B,40.46,39.46,34.44,46.22,44.27,-,-
39
+ perplexity-Research,40.46,39.10,35.65,46.11,43.08,82.63,31.20
40
+ grok-deeper-search,38.22,36.08,30.89,46.59,42.17,73.08,8.58
41
+ sonar-reasoning-pro,37.76,34.96,31.65,44.93,42.42,45.19,9.39
42
+ sonar-reasoning,37.75,34.73,32.59,44.42,42.39,52.58,13.37
43
+ claude-3-7-sonnet-with-search,36.63,35.95,31.29,44.05,36.07,87.32,24.51
44
+ sonar-pro,36.19,33.92,29.69,43.39,41.07,79.72,16.75
45
+ gemini-2.5-pro-preview-05-06,31.90,31.75,24.61,40.24,32.76,-,-
46
+ gpt-4o-search-preview,30.74,27.81,20.44,41.01,37.60,86.63,5.05
data/raw_data/1688AILab-DeepResearch-0325.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78e815652d8866916768b9962e688f76afc4d43bf4974a31ea8755ee64f111b
3
+ size 8497463
data/raw_data/RecallRadar.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bad563590f139bf0be0c11dd4444770bf7f646884254bf292a42ff8e2b125a
3
+ size 4527384
data/raw_data/TrajectoryKit.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c46731f1fba4d00493c5d911b1218f03900d3c99d0ff1b8ac2307521a4aa8e0
3
+ size 14628104
data/raw_data/baidu-qianfan-drs-pro.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7879685b02a64a5be7c38904e9c2a52e024d84968abfcd63e27ca6a2e2d71320
3
+ size 24233653
data/raw_data/baidu-qianfan-drs.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d68f0d753eda386faac31d1aa823e8779123362ba2627abe2a9bc25ce3307da
3
+ size 9653124
data/raw_data/claude-research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300f8dbc8242a5852bbe44098403f35fac1e4136e2274c93f0a3d659fee00d7f
3
+ size 1513379
data/raw_data/deepinsight.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab8f6258e6592b730a64646e3e00a02529094d9df0fc5a5ae9854ce0b0ca27f
3
+ size 18262702
data/raw_data/deepsynth.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74510d558e560367fb584abaae6bd75dca0220a52c9313749b571b8ebd9f4529
3
+ size 4491039
data/raw_data/doubao-deepresearch.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9512cedf730486da486ba9d0ec305213ca8176bd00b93da788367f090717f2
3
+ size 7451876
data/raw_data/dr-tulu.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5bb9fe8ea4311130e2135522360c5fe3241c541bcc8219950cfa05695d82c7
3
+ size 3738414
data/raw_data/drb_cellcog.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122de2712f7eab4e31553659b2a30ea61adf475ba8096d754c9dbc6a2a9630d7
3
+ size 6478126
data/raw_data/drb_cellcog_max.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e74304a73dd7cbb7d22c9c2c03b0c869dfb7c65edb19bf6fa1b3b804ccedaf
3
+ size 6773828
data/raw_data/gemini-2.5-pro-deepresearch.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ead8c3cc42c3ea844e71be7bf21670a608feaa5a718695e3b215247d9198a80
3
+ size 8553888
data/raw_data/gensee-search-gpt-5.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac0a4bdabdb1d1c1672e5272d99506018117c0e807d98981b9303d282a8f8c6
3
+ size 2086985
data/raw_data/grep-v4.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7905c50b5bf03aaee8e55693035cb3d956cffe30b8ba145371073a94dfdca0eb
3
+ size 7949984
data/raw_data/kimi-researcher.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3d49b2ef4a8aaa41e48a2e1d5b19dbf270eea29f4f06b8c01ced7c8b8f9830
3
+ size 5166726
data/raw_data/langchain-open-deep-research-gpt-5.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1217fe0b74d6cf5f634680c06157668d5a1ca35cc773706fe6bc2a889d08a896
3
+ size 2105329
data/raw_data/langchain-open-deep-research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83bfad2bdf5cb8de9593aaff20214f2588f8fedd8375f289a024c8ed69f2496a
3
+ size 1670658
data/raw_data/ms_deepresearch.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae66297928737ad9dd6e25f5e2889436726c2ea5e926b424dd180fe3494a067
3
+ size 10248221
data/raw_data/nvidia-aiq-nemotron-gpt52-updated.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d038f5cb04ba239694388386e839b979574e7c3c2fda5f05e4095732b5fc765d
3
+ size 7731077
data/raw_data/nvidia-aiq-research-assistant.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3392fe422c9762d2aee9b3da080e39fd73c90eadb7247617b0a5a4ac2521f83c
3
+ size 3467053
data/raw_data/onyx.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f63fa568ac4d3a80d2d015a64b2021037a8e174b304650607a404faf478375
3
+ size 4595651
data/raw_data/openai-deepresearch.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9dbbf7f18d8c985bc4d4f450089eb4bb73e77dbf7168a1bb4c81f811e06d84
3
+ size 6903838
data/raw_data/perplexity-Research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3b855862c99f108abf97b9e402b43eb4d3376c3ec93c2e0a9c871b70d0736e
3
+ size 1747879
data/raw_data/raaa-deep-research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b5da91ced190179430130321156f19005ee99bae412a55cca970dcac36a4c8
3
+ size 8310352
data/raw_data/salesforce-air-deep-research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766e080c9402ca0cb01e265b55c86201c6d273771bd57a4344f1e09984d9f12f
3
+ size 5192874
data/raw_data/tavily-research.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac4819e3936a09d340e2f3332e2ce5d4d18b5cfcf7e346c087e661bb2623ece
3
+ size 3195925
data/raw_data/thinkdepthai-deepresearch.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578ce210b003f68a2dd24ba2960c7cee8a63fe5fa826849e27dcf460baba4a8e
3
+ size 2694297
data/raw_data/tongyi-deepresearch-30B-A3B.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb8b3e967e2920e0ec5cf137ec43d972101f2fa1852df422f9ff2532c392307
3
+ size 969184
data/raw_data/xiaoyi_research_agent_0304.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97223e181c89e67182cc0afd1c2fcf5d54f5d8468d048c6391fb9054fdac86a8
3
+ size 11217138
data/raw_results/1688AILab-DeepResearch-0325/race_result.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Comprehensiveness: 0.5548
2
+ Insight: 0.5759
3
+ Instruction Following: 0.5338
4
+ Readability: 0.5350
5
+ Overall Score: 0.5539
data/raw_results/1688AILab-DeepResearch-0325/raw_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77e5325f6ba25155f1364c62a703ecf759377d0f8d89aa8780364fa776942e1
3
+ size 52197
data/raw_results/1688AILab-DeepResearch-0428/race_result.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Comprehensiveness: 0.5732
2
+ Insight: 0.5927
3
+ Instruction Following: 0.5351
4
+ Readability: 0.5336
5
+ Overall Score: 0.5653
data/raw_results/1688AILab-DeepResearch-0428/raw_results.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634f66d46b797f65dc032cce17f49e75726b9faf745bd7313b267f7ab38867f7
3
+ size 52188