Skip to content

[BFCL] Leaderboard Update - 2025/08/26 (Checkpoint 58f57e9) #1120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Aug 28, 2025
Merged

[BFCL] Leaderboard Update - 2025/08/26 (Checkpoint 58f57e9) #1120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
47ac059
update column headers
HuanzhiMao Jul 17, 2025
e608613
Merge remote-tracking branch 'origin/gh-pages' into leaderboard-update
HuanzhiMao Jul 18, 2025
70344ad
add csv files
HuanzhiMao Aug 28, 2025
c4cc5b1
Merge branch 'gh-pages' into leaderboard-update
HuanzhiMao Aug 28, 2025
13565e2
clean up
HuanzhiMao Aug 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 17 additions & 46 deletions assets/css/leaderboard_main.css
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,84 +18,55 @@
}

#leaderboard td:nth-child(4) {
background-color: #f09194;
background-color: #ff9999;
}

#leaderboard td:nth-child(5),
#leaderboard td:nth-child(6),
#leaderboard td:nth-child(7) {
background-color: #8f8fff;
background-color: #9eb3ff;
}

#leaderboard td:nth-child(8),
#leaderboard td:nth-child(9),
#leaderboard td:nth-child(10),
#leaderboard td:nth-child(11),
#leaderboard td:nth-child(12) {
background-color: #88ffc4;
background-color: #97e5b8;
}

#leaderboard td:nth-child(13),
#leaderboard td:nth-child(14),
#leaderboard td:nth-child(15),
#leaderboard td:nth-child(16),
#leaderboard td:nth-child(17) {
background-color: #75f1ff;
background-color: #7dd9e8;
}

#leaderboard td:nth-child(18),
#leaderboard td:nth-child(19),
#leaderboard td:nth-child(20),
#leaderboard td:nth-child(21),
#leaderboard td:nth-child(22) {
background-color: #ffdf75;
background-color: #ffd97a;
}

/* #leaderboard td:nth-child(23),
#leaderboard td:nth-child(23),
#leaderboard td:nth-child(24),
#leaderboard td:nth-child(25),
#leaderboard td:nth-child(26),
#leaderboard td:nth-child(27){
background-color: #efabdf;
} */


/* #leaderboard td:nth-child(8) {
background-color: #c0ff73;
}
#leaderboard td:nth-child(9) {
background-color: #ffdf75;
#leaderboard td:nth-child(27),
#leaderboard td:nth-child(28),
#leaderboard td:nth-child(29){
background-color: #d9a8ff;
}

#leaderboard td:nth-child(10) {
background-color: #d8787b;
}

#leaderboard td:nth-child(11),
#leaderboard td:nth-child(12),
#leaderboard td:nth-child(13) {
background-color: #8f8fff;
#leaderboard td:nth-child(30),
#leaderboard td:nth-child(31){
background-color: #ffb8d1;
}


#leaderboard td:nth-child(14),
#leaderboard td:nth-child(15),
#leaderboard td:nth-child(16),
#leaderboard td:nth-child(17) {
background-color: #75f1ff;
}


#leaderboard td:nth-child(18),
#leaderboard td:nth-child(19),
#leaderboard td:nth-child(20),
#leaderboard td:nth-child(21) {
background-color: #88ffc4;
}

#leaderboard td:nth-child(22) {
background-color: #c0ff73;
}
#leaderboard td:nth-child(23) {
background-color: #ffdf75;
} */
#leaderboard td:nth-child(32),
#leaderboard td:nth-child(33){
background-color: #ffcba4;
}
16 changes: 16 additions & 0 deletions data/forms/formHeaders.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,9 @@
{ "content": "", "class": "latency-top-header", "colspan": 4 },
{ "content": "Single Turn", "class": "nonliveast-top-header nonliveexec-top-header liveast-top-header", "colspan": 10 },
{ "content": "Multi Turn", "class": "multiturn-top-header", "colspan": 5 },
{ "content": "Agentic", "class": "websearch-top-header memory-top-header", "colspan": 7 },
{ "content": "Hallucination Measurement", "class": "", "colspan": 2 },
{ "content": "Format Sensitivity", "class": "", "colspan": 2 },
{ "content": "", "class": "", "colspan": 2 }
]
},
Expand All @@ -20,6 +22,9 @@
{ "content": "Non-live (AST)", "id":"nonliveast", "class": "nonliveast-header", "colspan": 5, "canExpand": true },
{ "content": "Live (AST)", "id":"liveast", "class": "liveast-header", "colspan": 5, "canExpand": true },
{ "content": "Multi turn", "id":"multiturn", "class": "multiturn-header", "colspan": 5, "canExpand": true },
{ "content": "Web Search", "id":"websearch", "class": "websearch-header", "colspan": 3, "canExpand": true },
{ "content": "Memory", "id":"memory", "class": "memory-header", "colspan": 4, "canExpand": true },
{ "content": "", "class": "", "colspan": 2 },
{ "content": "", "class": "", "colspan": 2 },
{ "content": "", "class": "", "colspan": 2 }
]
Expand Down Expand Up @@ -53,9 +58,20 @@
{ "content": "Miss Func", "class": "column-header multiturn-sub-header" },
{ "content": "Miss Param", "class": "column-header multiturn-sub-header" },
{ "content": "Long Context", "class": "column-header multiturn-sub-header" },

{ "content": "Overall Acc", "class": "column-header websearch-sub-header stay" },
{ "content": "Base", "class": "column-header websearch-sub-header" },
{ "content": "No Snippet", "class": "column-header websearch-sub-header" },

{ "content": "Overall Acc", "class": "column-header memory-sub-header stay" },
{ "content": "KV", "class": "column-header memory-sub-header" },
{ "content": "Vector", "class": "column-header memory-sub-header" },
{ "content": "Recursive Sum", "class": "column-header memory-sub-header" },

{ "content": "Relevance", "class": "column-header" },
{ "content": "Irrelevance", "class": "column-header" },
{ "content": "Max Delta", "class": "column-header" },
{ "content": "SD", "class": "column-header" },
{ "content": "Organization", "class": "column-header" },
{ "content": "License", "class": "column-header" }
]
Expand Down
119 changes: 119 additions & 0 deletions data_agentic.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,119 @@
Rank,Model,Agentic Overall Acc,Web Search Summary,Web Search Base,Web Search No Snippet,Memory Summary,Memory KV,Memory Vector,Memory Recursive Summarization
1,Claude-Sonnet-4-20250514 (FC),71.68%,84.00%,86.00%,82.00%,59.35%,40.65%,69.68%,67.74%
2,GPT-5-2025-08-07 (FC),71.07%,84.50%,86.00%,83.00%,57.63%,40.65%,60.65%,71.61%
3,Claude-Opus-4-1-20250805 (FC),69.58%,77.00%,82.00%,72.00%,62.15%,47.10%,61.94%,77.42%
4,Grok-4-0709 (FC),68.94%,72.50%,67.00%,78.00%,65.38%,57.42%,72.26%,66.45%
5,GLM-4.5 (FC),64.88%,79.00%,81.00%,77.00%,50.75%,40.65%,54.84%,56.77%
6,GPT-5-mini-2025-08-07 (FC),64.29%,84.50%,85.00%,84.00%,44.09%,33.55%,43.23%,55.48%
7,Grok-4-0709 (Prompt),63.20%,72.00%,71.00%,73.00%,54.41%,51.61%,54.19%,57.42%
8,GLM-4.5-Air (FC),60.51%,73.50%,75.00%,72.00%,47.53%,30.97%,57.42%,54.19%
9,o3-2025-04-16 (FC),59.54%,75.00%,74.00%,76.00%,44.09%,27.74%,38.06%,66.45%
10,o4-mini-2025-04-16 (FC),56.63%,78.00%,76.00%,80.00%,35.27%,18.71%,26.45%,60.65%
11,Gemini-2.5-Pro (Prompt),49.06%,66.50%,61.00%,72.00%,31.61%,29.03%,34.84%,30.97%
12,Gemini-2.5-Pro (FC),48.64%,60.50%,67.00%,54.00%,36.77%,32.26%,34.19%,43.87%
13,Moonshotai-Kimi-K2-Instruct (Prompt),48.49%,63.00%,65.00%,61.00%,33.98%,11.61%,35.48%,54.84%
14,GPT-5-nano-2025-08-07 (FC),48.33%,71.50%,78.00%,65.00%,25.16%,25.16%,23.23%,27.10%
15,Gemini-2.5-Flash (FC),46.69%,65.00%,62.00%,68.00%,28.39%,9.03%,22.58%,53.55%
16,o3-2025-04-16 (Prompt),44.98%,43.50%,47.00%,40.00%,46.45%,27.74%,45.81%,65.81%
17,o4-mini-2025-04-16 (Prompt),42.34%,55.00%,69.00%,41.00%,29.68%,19.35%,18.71%,50.97%
18,Moonshotai-Kimi-K2-Instruct (FC),42.08%,59.00%,69.00%,49.00%,25.16%,20.65%,18.71%,36.13%
19,Qwen3-235B-A22B-Instruct-2507 (FC),39.12%,49.00%,61.00%,37.00%,29.25%,14.19%,18.71%,54.84%
20,mistral-large-2411 (FC),35.72%,28.00%,35.00%,21.00%,43.44%,32.90%,47.74%,49.68%
21,Command A (FC),35.08%,46.50%,65.00%,28.00%,23.66%,10.97%,7.74%,52.26%
22,GPT-4o-2024-11-20 (FC),34.66%,40.50%,40.00%,41.00%,28.82%,14.84%,21.29%,50.32%
23,Amazon-Nova-Pro-v1:0 (FC),34.63%,34.00%,32.00%,36.00%,35.27%,19.35%,38.06%,48.39%
24,claude-3.5-haiku-20241022 (FC),31.81%,50.50%,58.00%,43.00%,13.12%,12.90%,20.65%,5.81%
25,DeepSeek-R1-0528 (FC),31.50%,63.00%,63.00%,63.00%,0.00%,0.00%,0.00%,0.00%
26,Gemini-2.5-Flash (Prompt),31.40%,40.00%,49.00%,31.00%,22.80%,10.97%,19.35%,38.06%
27,Mistral-Medium-2505 (FC),30.22%,37.00%,40.00%,34.00%,23.44%,6.45%,20.65%,43.23%
28,GPT-4o-mini-2024-07-18 (FC),30.15%,39.00%,41.00%,37.00%,21.29%,12.26%,22.58%,29.03%
29,Mistral-small-2506 (FC),30.01%,37.00%,36.00%,38.00%,23.01%,12.26%,14.19%,42.58%
30,DeepSeek-V3-0324 (FC),27.43%,32.50%,23.00%,42.00%,22.37%,10.32%,18.06%,38.71%
31,Qwen3-235B-A22B-Instruct-2507 (Prompt),27.15%,30.00%,31.00%,29.00%,24.30%,15.48%,12.26%,45.16%
32,Amazon-Nova-Lite-v1:0 (FC),25.56%,19.50%,23.00%,16.00%,31.61%,9.68%,33.55%,51.61%
33,Qwen3-32B (FC),25.47%,26.00%,27.00%,25.00%,24.95%,15.48%,20.65%,38.71%
34,Claude-Opus-4-1-20250805 (Prompt),24.94%,46.00%,46.00%,46.00%,3.87%,3.23%,4.52%,3.87%
35,Llama-4-Maverick-17B-128E-Instruct-FP8 (FC),23.17%,30.00%,44.00%,16.00%,16.34%,10.97%,24.52%,13.55%
36,Qwen3-14B (FC),22.83%,20.50%,26.00%,15.00%,25.16%,15.48%,17.42%,42.58%
37,QwQ-32B (Prompt),21.88%,28.50%,38.00%,19.00%,15.27%,12.26%,15.48%,18.06%
38,GPT-5-2025-08-07 (Prompt),20.99%,5.00%,4.00%,6.00%,36.99%,24.52%,36.13%,50.32%
39,watt-tool-70B (FC),20.71%,22.50%,31.00%,14.00%,18.92%,6.45%,25.16%,25.16%
40,Qwen3-30B-A3B-Instruct-2507 (FC),20.47%,20.50%,24.00%,17.00%,20.43%,16.13%,13.55%,31.61%
41,Qwen3-32B (Prompt),20.35%,26.50%,32.00%,21.00%,14.19%,9.03%,10.97%,22.58%
42,Mistral-Medium-2505,19.99%,23.00%,35.00%,11.00%,16.99%,8.39%,16.77%,25.81%
43,xLAM-2-32b-fc-r (FC),19.64%,22.50%,31.00%,14.00%,16.77%,8.39%,10.32%,31.61%
44,Qwen3-14B (Prompt),19.48%,28.00%,34.00%,22.00%,10.97%,6.45%,6.45%,20.00%
45,CoALM-405B,18.89%,21.00%,34.00%,8.00%,16.77%,2.58%,29.68%,18.06%
46,QwQ-32B (FC),18.01%,10.00%,12.00%,8.00%,26.02%,14.19%,16.13%,47.74%
47,Claude-Sonnet-4-20250514 (Prompt),17.19%,29.00%,28.00%,30.00%,5.38%,3.87%,1.94%,10.32%
48,Gemini-2.5-Flash-Lite-Preview-06-17 (FC),16.98%,27.50%,40.00%,15.00%,6.45%,2.58%,3.23%,13.55%
49,Qwen3-8B (FC),16.96%,15.00%,19.00%,11.00%,18.92%,14.84%,14.84%,27.10%
50,claude-3.5-haiku-20241022 (Prompt),16.59%,23.50%,30.00%,17.00%,9.68%,11.61%,12.26%,5.16%
51,xLAM-2-70b-fc-r (FC),16.07%,14.50%,13.00%,16.00%,17.63%,5.16%,11.61%,36.13%
52,GPT-5-mini-2025-08-07 (Prompt),15.96%,14.50%,16.00%,13.00%,17.42%,14.84%,18.06%,19.35%
53,mistral-large-2411 (Prompt),15.82%,12.50%,22.00%,3.00%,19.14%,16.13%,18.71%,22.58%
54,Qwen3-30B-A3B-Instruct-2507 (Prompt),15.16%,20.00%,26.00%,14.00%,10.32%,7.10%,8.39%,15.48%
55,Qwen3-8B (Prompt),15.06%,17.00%,16.00%,18.00%,13.12%,3.87%,11.61%,23.87%
56,Amazon-Nova-Micro-v1:0 (FC),14.83%,6.00%,7.00%,5.00%,23.66%,5.16%,15.48%,50.32%
57,ToolACE-2-8B (FC),14.82%,9.00%,13.00%,5.00%,20.65%,7.74%,18.06%,36.13%
58,Phi-4 (Prompt),14.22%,5.00%,6.00%,4.00%,23.44%,11.61%,20.65%,38.06%
59,Falcon3-10B-Instruct (FC),13.76%,3.00%,2.00%,4.00%,24.52%,8.39%,20.00%,45.16%
60,GPT-5-nano-2025-08-07 (Prompt),13.63%,12.00%,14.00%,10.00%,15.27%,12.90%,14.84%,18.06%
61,Gemma-3-12b-it (Prompt),13.43%,4.50%,5.00%,4.00%,22.37%,9.68%,18.71%,38.71%
62,Mistral-Small-2506 (Prompt),13.07%,8.50%,8.00%,9.00%,17.63%,4.52%,9.68%,38.71%
63,Llama-3.1-70B-Instruct (Prompt),11.66%,14.50%,16.00%,13.00%,8.82%,5.16%,9.03%,12.26%
64,Falcon3-7B-Instruct (FC),11.22%,2.00%,2.00%,2.00%,20.43%,12.26%,16.13%,32.90%
65,xLAM-2-8b-fc-r (FC),10.85%,6.00%,8.00%,4.00%,15.70%,4.52%,14.19%,28.39%
66,Qwen3-4B-Instruct-2507 (FC),10.68%,2.00%,4.00%,0.00%,19.35%,11.61%,17.42%,29.03%
67,Gemini-2.5-Flash-Lite-Preview-06-17 (Prompt),9.89%,1.50%,2.00%,1.00%,18.28%,0.65%,14.19%,40.00%
68,Command R7B (FC),9.01%,10.50%,9.00%,12.00%,7.53%,9.68%,9.68%,3.23%
69,Arch-Agent-32B,8.92%,3.00%,5.00%,1.00%,14.84%,9.03%,13.55%,21.94%
70,Qwen3-4B-Instruct-2507 (Prompt),8.84%,5.00%,4.00%,6.00%,12.69%,11.61%,11.61%,14.84%
71,Llama-3.3-70B-Instruct (FC),8.84%,9.50%,13.00%,6.00%,8.17%,5.16%,7.74%,11.61%
72,Llama-3.1-8B-Instruct (FC),8.78%,1.00%,1.00%,1.00%,16.56%,6.45%,14.19%,29.03%
73,Llama-4-Scout-17B-16E-Instruct (FC),8.62%,11.00%,15.00%,7.00%,6.24%,4.52%,3.23%,10.97%
74,GPT-4o-mini-2024-07-18 (Prompt),8.59%,6.00%,7.00%,5.00%,11.18%,9.03%,3.87%,20.65%
75,BitAgent-8B,8.24%,4.00%,4.00%,4.00%,12.47%,4.52%,20.65%,12.26%
76,Granite-3.1-8B-Instruct (FC),7.60%,1.00%,2.00%,0.00%,14.19%,6.45%,6.45%,29.68%
77,xLAM-2-3b-fc-r (FC),7.42%,1.50%,1.00%,2.00%,13.33%,4.52%,10.97%,24.52%
78,Llama-3.1-70B-Instruct (FC),7.41%,4.50%,4.00%,5.00%,10.32%,5.81%,3.87%,21.29%
79,Open-Mistral-Nemo-2407 (FC),7.34%,2.00%,3.00%,1.00%,12.69%,14.84%,11.61%,11.61%
80,Gemma-3-27b-it (Prompt),7.13%,0.50%,1.00%,0.00%,13.76%,1.94%,0.65%,38.71%
81,palmyra-x-004 (FC),7.13%,2.00%,3.00%,1.00%,12.26%,9.68%,9.68%,17.42%
82,Llama-3.1-8B-Instruct (Prompt),7.02%,3.50%,6.00%,1.00%,10.54%,4.52%,5.81%,21.29%
83,Haha-7B,6.84%,1.00%,2.00%,0.00%,12.69%,5.16%,2.58%,30.32%
84,Gemma-3-4b-it (Prompt),6.41%,1.00%,1.00%,1.00%,11.83%,7.74%,12.90%,14.84%
85,watt-tool-8B (FC),6.30%,4.00%,7.00%,1.00%,8.60%,3.87%,13.55%,8.39%
86,DeepSeek-R1-0528 (Prompt),6.25%,12.50%,21.00%,4.00%,0.00%,0.00%,0.00%,0.00%
87,GPT-4o-2024-11-20 (Prompt),6.23%,3.00%,2.00%,4.00%,9.46%,7.10%,5.16%,16.13%
88,MiniCPM3-4B-FC (FC),6.06%,0.50%,1.00%,0.00%,11.61%,11.61%,14.19%,9.03%
89,Bielik-11B-v2.3-Instruct (Prompt),5.95%,2.00%,2.00%,2.00%,9.89%,5.81%,1.94%,21.94%
90,Open-Mistral-Nemo-2407 (Prompt),5.69%,3.00%,3.00%,3.00%,8.39%,10.32%,10.32%,4.52%
91,Granite-3.2-8B-Instruct (FC),5.59%,0.00%,0.00%,0.00%,11.18%,7.74%,10.32%,15.48%
92,Qwen3-1.7B (FC),5.58%,4.50%,5.00%,4.00%,6.67%,5.16%,2.58%,12.26%
93,MiniCPM3-4B (Prompt),5.09%,2.00%,2.00%,2.00%,8.17%,10.97%,7.74%,5.81%
94,Qwen3-0.6B (FC),4.95%,0.00%,0.00%,0.00%,9.89%,4.52%,6.45%,18.71%
95,Ministral-8B-Instruct-2410 (FC),4.76%,3.50%,4.00%,3.00%,6.02%,4.52%,5.81%,7.74%
96,GLM-4-9b-Chat (FC),4.73%,0.00%,0.00%,0.00%,9.46%,5.16%,6.45%,16.77%
97,xLAM-2-1b-fc-r (FC),4.48%,1.00%,1.00%,1.00%,7.96%,10.32%,5.81%,7.74%
98,Falcon3-3B-Instruct (FC),4.16%,1.00%,1.00%,1.00%,7.31%,3.23%,11.61%,7.10%
99,RZN-T (Prompt),3.94%,1.00%,1.00%,1.00%,6.88%,3.87%,2.58%,14.19%
100,Arch-Agent-1.5B,3.87%,1.50%,2.00%,1.00%,6.24%,4.52%,5.16%,9.03%
101,Qwen3-1.7B (Prompt),3.76%,3.00%,3.00%,3.00%,4.52%,1.29%,8.39%,3.87%
102,Arch-Agent-3B,3.73%,1.00%,0.00%,2.00%,6.45%,6.45%,6.45%,6.45%
103,Llama-3.2-3B-Instruct (FC),2.83%,0.50%,1.00%,0.00%,5.16%,4.52%,1.94%,9.03%
104,Phi-4-mini-instruct (FC),2.51%,2.00%,1.00%,3.00%,3.01%,0.00%,2.58%,6.45%
105,CoALM-70B,2.47%,0.00%,0.00%,0.00%,4.95%,6.45%,5.16%,3.23%
106,ThinkAgent-1B (FC),1.93%,1.50%,2.00%,1.00%,2.37%,0.65%,3.23%,3.23%
107,Gemma-3-1b-it (Prompt),1.61%,0.00%,0.00%,0.00%,3.23%,4.52%,3.87%,1.29%
108,Llama-3.2-1B-Instruct (FC),1.61%,0.00%,0.00%,0.00%,3.23%,1.29%,2.58%,5.81%
109,CoALM-8B,1.51%,0.00%,0.00%,0.00%,3.01%,3.87%,3.87%,1.29%
110,Qwen3-0.6B (Prompt),1.43%,0.50%,0.00%,1.00%,2.37%,1.29%,0.00%,5.81%
111,DM-Cito-8B-v2 (Prompt),1.43%,0.50%,0.00%,1.00%,2.37%,0.00%,0.65%,6.45%
112,BitAgent-Bounty-8B,1.33%,0.50%,1.00%,0.00%,2.15%,0.65%,1.94%,3.87%
113,Hammer2.1-3b (FC),0.54%,0.00%,0.00%,0.00%,1.08%,1.29%,0.00%,1.94%
114,Falcon3-1B-Instruct (FC),0.54%,0.00%,0.00%,0.00%,1.08%,1.29%,1.94%,0.00%
115,Hammer2.1-0.5b (FC),0.32%,0.00%,0.00%,0.00%,0.65%,0.65%,0.00%,1.29%
116,Granite-20b-FunctionCalling (FC),0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%
117,Hammer2.1-1.5b (FC),0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%
118,Hammer2.1-7b (FC),0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%
Loading