Skip to content

Commit a53acce

Browse files
authored
[BFCL] Leaderboard Update - 2025/06/14 (Checkpoint 1bb65c9) (#1053)
This PR updates the leaderboard to reflect the change in score due to the following PR merge: 1. #1014 2. #1031 3. #1015 4. #1033 5. #1040 6. #1017 7. #1061 8. #1056 9. #1064 10. #1032 Models were evaluated using checkpoint commit 1bb65c9.
1 parent 4147457 commit a53acce

File tree

6 files changed

+415
-462
lines changed

6 files changed

+415
-462
lines changed

data_live.csv

Lines changed: 105 additions & 117 deletions
Original file line numberDiff line numberDiff line change
@@ -1,122 +1,110 @@
11
Rank,Model,Live Overall Acc,AST Summary,Python Simple AST,Python Multiple AST,Python Parallel AST,Python Parallel Multiple AST,Irrelevance Detection,Relevance Detection
22
1,GPT-4.5-Preview-2025-02-27 (Prompt),82.99%,82.90%,87.98%,81.86%,93.75%,66.67%,83.45%,66.67%
3-
2,Gemini-2.5-Pro-Exp-03-25 (Prompt),81.47%,82.01%,87.21%,80.53%,93.75%,83.33%,80.95%,66.67%
4-
3,Gemini-2.0-Flash-001 (Prompt),81.39%,73.87%,75.58%,73.12%,81.25%,83.33%,93.42%,55.56%
5-
4,Grok-3-mini-beta (FC),80.72%,76.09%,82.17%,77.49%,0.00%,0.00%,88.32%,55.56%
6-
5,o1-2024-12-17 (Prompt),80.63%,77.79%,82.95%,76.54%,81.25%,75.00%,85.15%,72.22%
7-
6,Command A (FC),80.45%,78.76%,84.50%,77.68%,81.25%,62.50%,83.22%,72.22%
8-
7,Mistral-small-2503 (FC),80.14%,73.87%,65.89%,76.45%,56.25%,58.33%,89.91%,72.22%
9-
8,ToolACE-2-8B (FC),80.05%,77.05%,70.93%,79.01%,81.25%,54.17%,84.81%,72.22%
10-
9,GPT-4.1-2025-04-14 (FC),79.92%,78.39%,80.23%,78.35%,68.75%,66.67%,82.31%,77.78%
11-
10,GPT-4o-2024-11-20 (Prompt),79.88%,80.24%,84.50%,79.30%,87.50%,70.83%,79.48%,72.22%
12-
11,Qwen2.5-32B-Instruct (FC),79.69%,79.35%,80.23%,80.06%,43.75%,62.50%,80.50%,64.71%
13-
12,Gemini-2.0-Flash-Lite-001 (Prompt),79.61%,75.28%,79.07%,74.74%,75.00%,58.33%,86.51%,66.67%
14-
13,GPT-4.5-Preview-2025-02-27 (FC),79.34%,78.68%,80.23%,78.63%,68.75%,70.83%,80.61%,66.67%
15-
14,Gemini-2.0-Flash-001 (FC),79.12%,69.58%,74.42%,68.28%,81.25%,66.67%,94.33%,50.00%
16-
15,o3-mini-2025-01-31 (Prompt),79.08%,78.24%,82.95%,77.11%,87.50%,70.83%,80.50%,72.22%
17-
16,Qwen2.5-72B-Instruct (FC),78.98%,78.02%,79.84%,78.25%,56.25%,62.50%,80.61%,70.59%
18-
17,Claude-3.5-Sonnet-20241022 (FC),78.94%,80.61%,84.11%,81.96%,25.00%,20.83%,76.42%,77.78%
19-
18,GPT-4o-2024-11-20 (FC),78.85%,79.05%,81.01%,78.54%,81.25%,79.17%,78.46%,83.33%
20-
19,Claude-3.7-Sonnet-20250219 (FC),78.41%,75.35%,82.56%,76.45%,0.00%,0.00%,83.22%,72.22%
21-
20,GPT-4.1-2025-04-14 (Prompt),78.32%,78.46%,85.66%,76.54%,93.75%,75.00%,77.89%,88.89%
22-
21,GPT-4.1-mini-2025-04-14 (FC),78.05%,78.09%,80.62%,77.78%,75.00%,66.67%,78.12%,72.22%
23-
22,Claude-3-Opus-20240229 (FC),78.05%,75.20%,79.07%,75.78%,31.25%,37.50%,82.77%,61.11%
24-
23,o1-2024-12-17 (FC),78.01%,77.20%,81.78%,79.01%,0.00%,0.00%,79.37%,72.22%
25-
24,watt-tool-70B (FC),77.74%,83.57%,86.05%,83.48%,81.25%,62.50%,68.48%,94.44%
26-
25,Gemini-2.5-Pro-Exp-03-25 (FC),77.70%,68.17%,79.46%,64.96%,81.25%,79.17%,92.97%,44.44%
27-
26,o3-mini-2025-01-31 (FC),77.30%,76.83%,81.40%,78.63%,0.00%,0.00%,78.00%,77.78%
28-
27,Gemini-2.0-Flash-Lite-001 (FC),77.25%,68.10%,71.32%,67.05%,81.25%,70.83%,91.84%,50.00%
29-
28,palmyra-x-004 (FC),77.21%,69.58%,76.36%,68.38%,50.00%,62.50%,89.00%,72.22%
30-
29,Qwen2.5-14B-Instruct (FC),76.68%,75.35%,77.13%,75.02%,75.00%,70.83%,79.14%,55.56%
31-
30,Functionary-Medium-v3.1 (FC),76.63%,82.61%,81.78%,83.29%,68.75%,70.83%,67.57%,72.22%
32-
31,watt-tool-8B (FC),76.50%,77.35%,76.74%,77.49%,87.50%,70.83%,75.06%,83.33%
33-
32,GPT-4o-mini-2024-07-18 (Prompt),76.50%,77.87%,81.40%,76.73%,93.75%,79.17%,74.26%,83.33%
34-
33,Gemma-3-27b-it (Prompt),76.37%,80.16%,86.43%,78.73%,93.75%,66.67%,70.41%,83.33%
35-
34,BitAgent-8B,76.14%,77.50%,77.91%,77.40%,87.50%,70.83%,73.92%,83.33%
36-
35,mistral-large-2411 (FC),76.06%,80.53%,87.21%,79.01%,81.25%,75.00%,69.05%,83.33%
37-
36,Gemini-2.0-Flash-Thinking-Exp-01-21 (Prompt),75.97%,82.24%,86.43%,81.01%,87.50%,87.50%,66.33%,77.78%
38-
37,Qwen/QwQ-32B (FC) (Novita),75.48%,80.01%,81.01%,79.68%,87.50%,79.17%,68.71%,66.67%
39-
38,Qwen2.5-72B-Instruct (Prompt),75.30%,82.38%,85.27%,82.15%,62.50%,75.00%,63.95%,100.00%
40-
39,Hammer2.1-7b (FC),75.11%,77.20%,76.74%,77.40%,81.25%,70.83%,71.77%,82.35%
41-
40,xiaoming-14B (Prompt),74.77%,76.54%,81.78%,75.88%,62.50%,58.33%,72.00%,77.78%
42-
41,CoALM-405B,74.50%,83.20%,84.88%,83.00%,87.50%,70.83%,60.66%,100.00%
43-
42,GPT-4o-mini-2024-07-18 (FC),74.41%,76.68%,78.68%,76.16%,87.50%,70.83%,70.75%,83.33%
44-
43,DeepSeek-R1 (Prompt),74.41%,80.61%,84.11%,79.87%,87.50%,70.83%,65.08%,66.67%
45-
44,Amazon-Nova-Pro-v1:0 (FC),74.32%,77.72%,80.23%,77.49%,81.25%,58.33%,69.05%,77.78%
46-
45,xLAM-2-32b-fc-r (FC),74.23%,76.17%,82.95%,75.21%,56.25%,58.33%,70.98%,88.89%
47-
46,Qwen2.5-32B-Instruct (Prompt),74.23%,78.83%,82.95%,78.54%,62.50%,58.33%,66.67%,100.00%
48-
47,Qwen2.5-7B-Instruct (FC),74.19%,75.35%,75.58%,75.59%,68.75%,66.67%,72.34%,77.78%
49-
48,Haha-7B,74.19%,77.57%,78.29%,77.59%,75.00%,70.83%,68.82%,83.33%
50-
49,Qwen2.5-14B-Instruct (Prompt),74.14%,75.20%,74.42%,75.78%,62.50%,66.67%,72.45%,77.78%
51-
50,Hammer2.1-3b (FC),74.04%,73.06%,73.26%,73.31%,62.50%,66.67%,75.40%,82.35%
52-
51,GoGoAgent,74.01%,74.69%,72.87%,75.40%,68.75%,66.67%,72.90%,77.78%
53-
52,Functionary-Small-v3.1 (FC),73.75%,78.24%,79.84%,78.16%,81.25%,62.50%,66.78%,77.78%
54-
53,xLAM-2-70b-fc-r (FC),72.95%,72.02%,77.13%,71.13%,68.75%,58.33%,74.49%,66.67%
55-
54,CoALM-8B,72.95%,67.28%,71.71%,66.67%,56.25%,54.17%,81.41%,83.33%
56-
55,claude-3.5-haiku-20241022 (FC),72.37%,77.13%,82.95%,78.35%,18.75%,0.00%,64.85%,83.33%
57-
56,Claude-3.5-Sonnet-20241022 (Prompt),71.97%,80.75%,86.82%,80.06%,81.25%,45.83%,58.39%,77.78%
58-
57,CoALM-70B,71.92%,66.17%,70.16%,65.34%,68.75%,58.33%,80.84%,66.67%
59-
58,Amazon-Nova-Lite-v1:0 (FC),71.61%,70.61%,72.87%,70.09%,75.00%,66.67%,73.24%,66.67%
60-
59,Grok-3-beta (FC),71.21%,75.35%,83.72%,76.16%,0.00%,0.00%,64.85%,72.22%
61-
60,GPT-4.1-mini-2025-04-14 (Prompt),71.17%,72.61%,79.46%,70.94%,75.00%,70.83%,68.71%,83.33%
62-
61,claude-3.5-haiku-20241022 (Prompt),70.77%,76.68%,84.88%,75.02%,87.50%,54.17%,61.56%,77.78%
63-
62,Hammer2.1-1.5b (FC),70.64%,69.73%,71.32%,69.80%,50.00%,62.50%,71.88%,77.78%
64-
63,MiniCPM3-4B-FC (FC),70.01%,65.73%,74.81%,63.91%,43.75%,62.50%,76.53%,72.22%
65-
64,Grok-3-beta (Prompt),69.61%,81.87%,86.05%,81.20%,75.00%,70.83%,50.23%,100.00%
66-
65,Qwen2.5-3B-Instruct (FC),69.39%,71.87%,74.03%,72.08%,62.50%,45.83%,65.19%,88.89%
67-
66,Command R7B (FC),69.17%,59.59%,63.18%,58.69%,56.25%,62.50%,84.13%,55.56%
68-
67,DeepSeek-V3 (FC),68.41%,82.09%,83.72%,82.15%,81.25%,62.50%,47.05%,88.89%
3+
2,Gemini-2.0-Flash-001 (Prompt),81.39%,73.87%,75.58%,73.12%,81.25%,83.33%,93.42%,55.56%
4+
3,Qwen3-30B-A3B (FC),81.34%,82.38%,86.82%,81.20%,81.25%,87.50%,79.93%,72.22%
5+
4,Llama-3.1-Nemotron-Ultra-253B-v1 (FC),80.76%,82.75%,86.43%,82.24%,75.00%,70.83%,77.66%,83.33%
6+
5,DM-Cito-8B (Prompt),80.72%,79.27%,84.50%,78.25%,81.25%,66.67%,83.22%,66.67%
7+
6,Grok-3-mini-beta (FC),80.72%,76.09%,82.17%,77.49%,0.00%,0.00%,88.32%,55.56%
8+
7,o1-2024-12-17 (Prompt),80.63%,77.79%,82.95%,76.54%,81.25%,75.00%,85.15%,72.22%
9+
8,Command A (FC),80.45%,78.76%,84.50%,77.68%,81.25%,62.50%,83.22%,72.22%
10+
9,Mistral-small-2503 (FC),80.14%,73.87%,65.89%,76.45%,56.25%,58.33%,89.91%,72.22%
11+
10,ToolACE-2-8B (FC),80.05%,77.05%,70.93%,79.01%,81.25%,54.17%,84.81%,72.22%
12+
11,Qwen3-14B (FC),79.96%,81.72%,86.05%,80.82%,68.75%,83.33%,77.44%,72.22%
13+
12,GPT-4.1-2025-04-14 (FC),79.92%,78.39%,80.23%,78.35%,68.75%,66.67%,82.31%,77.78%
14+
13,GPT-4o-2024-11-20 (Prompt),79.88%,80.24%,84.50%,79.30%,87.50%,70.83%,79.48%,72.22%
15+
14,Gemini-2.0-Flash-Lite-001 (Prompt),79.61%,75.28%,79.07%,74.74%,75.00%,58.33%,86.51%,66.67%
16+
15,GPT-4.5-Preview-2025-02-27 (FC),79.34%,78.68%,80.23%,78.63%,68.75%,70.83%,80.61%,66.67%
17+
16,Gemini-2.0-Flash-001 (FC),79.12%,69.58%,74.42%,68.28%,81.25%,66.67%,94.33%,50.00%
18+
17,o3-mini-2025-01-31 (Prompt),79.08%,78.24%,82.95%,77.11%,87.50%,70.83%,80.50%,72.22%
19+
18,Claude-3.5-Sonnet-20241022 (FC),78.94%,80.61%,84.11%,81.96%,25.00%,20.83%,76.42%,77.78%
20+
19,GPT-4o-2024-11-20 (FC),78.85%,79.05%,81.01%,78.54%,81.25%,79.17%,78.46%,83.33%
21+
20,Qwen3-4B (FC),78.72%,81.42%,87.60%,79.96%,75.00%,83.33%,74.72%,72.22%
22+
21,Qwen3-8B (FC),78.54%,80.16%,84.88%,79.39%,62.50%,75.00%,76.08%,77.78%
23+
22,Claude-3.7-Sonnet-20250219 (FC),78.41%,75.35%,82.56%,76.45%,0.00%,0.00%,83.22%,72.22%
24+
23,GPT-4.1-2025-04-14 (Prompt),78.32%,78.46%,85.66%,76.54%,93.75%,75.00%,77.89%,88.89%
25+
24,GPT-4.1-mini-2025-04-14 (FC),78.05%,78.09%,80.62%,77.78%,75.00%,66.67%,78.12%,72.22%
26+
25,Claude-3-Opus-20240229 (FC),78.05%,75.20%,79.07%,75.78%,31.25%,37.50%,82.77%,61.11%
27+
26,o1-2024-12-17 (FC),78.01%,77.20%,81.78%,79.01%,0.00%,0.00%,79.37%,72.22%
28+
27,Qwen3-32B (FC),77.83%,80.90%,84.11%,80.72%,68.75%,62.50%,73.24%,72.22%
29+
28,watt-tool-70B (FC),77.74%,83.57%,86.05%,83.48%,81.25%,62.50%,68.48%,94.44%
30+
29,DeepSeek-V3-0324 (FC),77.34%,80.38%,86.05%,79.49%,75.00%,62.50%,72.56%,83.33%
31+
30,o3-mini-2025-01-31 (FC),77.30%,76.83%,81.40%,78.63%,0.00%,0.00%,78.00%,77.78%
32+
31,DeepSeek-R1-0528 (FC),77.30%,80.46%,85.66%,79.68%,87.50%,54.17%,72.45%,77.78%
33+
32,Grok-3-beta (FC),77.25%,77.72%,80.62%,77.40%,56.25%,75.00%,76.76%,66.67%
34+
33,Gemini-2.0-Flash-Lite-001 (FC),77.25%,68.10%,71.32%,67.05%,81.25%,70.83%,91.84%,50.00%
35+
34,palmyra-x-004 (FC),77.21%,69.58%,76.36%,68.38%,50.00%,62.50%,89.00%,72.22%
36+
35,Qwen3-235B-A22B (FC),77.03%,80.90%,87.21%,79.30%,81.25%,83.33%,70.98%,83.33%
37+
36,Functionary-Medium-v3.1 (FC),76.63%,82.61%,81.78%,83.29%,68.75%,70.83%,67.57%,72.22%
38+
37,watt-tool-8B (FC),76.50%,77.35%,76.74%,77.49%,87.50%,70.83%,75.06%,83.33%
39+
38,GPT-4o-mini-2024-07-18 (Prompt),76.50%,77.87%,81.40%,76.73%,93.75%,79.17%,74.26%,83.33%
40+
39,Gemma-3-27b-it (Prompt),76.37%,80.16%,86.43%,78.73%,93.75%,66.67%,70.41%,83.33%
41+
40,BitAgent-8B,76.14%,77.50%,77.91%,77.40%,87.50%,70.83%,73.92%,83.33%
42+
41,mistral-large-2411 (FC),76.06%,80.53%,87.21%,79.01%,81.25%,75.00%,69.05%,83.33%
43+
42,Gemini-2.0-Flash-Thinking-Exp-01-21 (Prompt),75.97%,82.24%,86.43%,81.01%,87.50%,87.50%,66.33%,77.78%
44+
43,QwQ-32B (FC),75.61%,79.57%,80.62%,79.20%,81.25%,83.33%,69.39%,83.33%
45+
44,Hammer2.1-7b (FC),75.11%,77.20%,76.74%,77.40%,81.25%,70.83%,71.77%,82.35%
46+
45,xiaoming-14B (Prompt),74.77%,76.54%,81.78%,75.88%,62.50%,58.33%,72.00%,77.78%
47+
46,Gemini-2.5-Pro-Preview-05-06 (FC),74.59%,65.28%,77.91%,62.20%,68.75%,62.50%,89.68%,33.33%
48+
47,CoALM-405B,74.50%,83.20%,84.88%,83.00%,87.50%,70.83%,60.66%,100.00%
49+
48,GPT-4o-mini-2024-07-18 (FC),74.41%,76.68%,78.68%,76.16%,87.50%,70.83%,70.75%,83.33%
50+
49,Amazon-Nova-Pro-v1:0 (FC),74.32%,77.72%,80.23%,77.49%,81.25%,58.33%,69.05%,77.78%
51+
50,xLAM-2-32b-fc-r (FC),74.23%,76.17%,82.95%,75.21%,56.25%,58.33%,70.98%,88.89%
52+
51,Hammer2.1-3b (FC),74.04%,73.06%,73.26%,73.31%,62.50%,66.67%,75.40%,82.35%
53+
52,GoGoAgent,74.01%,74.69%,72.87%,75.40%,68.75%,66.67%,72.90%,77.78%
54+
53,Functionary-Small-v3.1 (FC),73.75%,78.24%,79.84%,78.16%,81.25%,62.50%,66.78%,77.78%
55+
54,xLAM-2-70b-fc-r (FC),72.95%,72.02%,77.13%,71.13%,68.75%,58.33%,74.49%,66.67%
56+
55,Qwen3-1.7B (FC),72.95%,73.28%,75.58%,72.65%,75.00%,75.00%,72.68%,61.11%
57+
56,CoALM-8B,72.95%,67.28%,71.71%,66.67%,56.25%,54.17%,81.41%,83.33%
58+
57,claude-3.5-haiku-20241022 (FC),72.37%,77.13%,82.95%,78.35%,18.75%,0.00%,64.85%,83.33%
59+
58,Claude-3.5-Sonnet-20241022 (Prompt),71.97%,80.75%,86.82%,80.06%,81.25%,45.83%,58.39%,77.78%
60+
59,CoALM-70B,71.92%,66.17%,70.16%,65.34%,68.75%,58.33%,80.84%,66.67%
61+
60,Amazon-Nova-Lite-v1:0 (FC),71.61%,70.61%,72.87%,70.09%,75.00%,66.67%,73.24%,66.67%
62+
61,ling-lite-v1.5 (Prompt),71.26%,71.80%,74.42%,71.13%,75.00%,70.83%,70.07%,88.89%
63+
62,GPT-4.1-mini-2025-04-14 (Prompt),71.17%,72.61%,79.46%,70.94%,75.00%,70.83%,68.71%,83.33%
64+
63,claude-3.5-haiku-20241022 (Prompt),70.77%,76.68%,84.88%,75.02%,87.50%,54.17%,61.56%,77.78%
65+
64,Hammer2.1-1.5b (FC),70.64%,69.73%,71.32%,69.80%,50.00%,62.50%,71.88%,77.78%
66+
65,MiniCPM3-4B-FC (FC),70.01%,65.73%,74.81%,63.91%,43.75%,62.50%,76.53%,72.22%
67+
66,Grok-3-beta (Prompt),69.61%,81.87%,86.05%,81.20%,75.00%,70.83%,50.23%,100.00%
68+
67,Command R7B (FC),69.17%,59.59%,63.18%,58.69%,56.25%,62.50%,84.13%,55.56%
6969
68,Sky-T1-32B-Preview (Prompt),68.00%,76.76%,77.52%,77.11%,62.50%,62.50%,54.08%,94.12%
70-
69,Qwen2.5-7B-Instruct (Prompt),67.44%,75.06%,76.74%,74.93%,62.50%,70.83%,55.33%,88.89%
71-
70,Gemma-3-12b-it (Prompt),67.13%,73.58%,84.88%,70.85%,87.50%,62.50%,56.80%,88.89%
72-
71,Amazon-Nova-Micro-v1:0 (FC),67.04%,64.17%,65.89%,64.20%,62.50%,45.83%,71.32%,72.22%
73-
72,Claude-3-Opus-20240229 (Prompt),66.99%,79.72%,85.27%,79.11%,68.75%,54.17%,47.17%,83.33%
74-
73,xLAM-2-8b-fc-r (FC),66.90%,67.51%,74.81%,66.29%,56.25%,50.00%,65.76%,77.78%
75-
74,GLM-4-9b-Chat (FC),66.81%,64.03%,72.48%,64.39%,0.00%,0.00%,71.09%,66.67%
76-
75,Phi-4 (Prompt),66.28%,56.11%,62.79%,53.94%,75.00%,66.67%,81.86%,66.67%
77-
76,Open-Mistral-Nemo-2407 (FC),65.97%,71.13%,77.13%,69.61%,75.00%,70.83%,58.05%,66.67%
78-
77,Claude-3.7-Sonnet-20250219 (Prompt),65.79%,83.64%,87.98%,83.57%,68.75%,50.00%,37.76%,100.00%
79-
78,FireFunction-v2 (FC),65.66%,78.09%,79.07%,78.35%,56.25%,70.83%,46.03%,94.44%
70+
69,Gemma-3-12b-it (Prompt),67.13%,73.58%,84.88%,70.85%,87.50%,62.50%,56.80%,88.89%
71+
70,Amazon-Nova-Micro-v1:0 (FC),67.04%,64.17%,65.89%,64.20%,62.50%,45.83%,71.32%,72.22%
72+
71,Claude-3-Opus-20240229 (Prompt),66.99%,79.72%,85.27%,79.11%,68.75%,54.17%,47.17%,83.33%
73+
72,xLAM-2-8b-fc-r (FC),66.90%,67.51%,74.81%,66.29%,56.25%,50.00%,65.76%,77.78%
74+
73,GLM-4-9b-Chat (FC),66.81%,64.03%,72.48%,64.39%,0.00%,0.00%,71.09%,66.67%
75+
74,Phi-4 (Prompt),66.28%,56.11%,62.79%,53.94%,75.00%,66.67%,81.86%,66.67%
76+
75,Open-Mistral-Nemo-2407 (FC),65.97%,71.13%,77.13%,69.61%,75.00%,70.83%,58.05%,66.67%
77+
76,Claude-3.7-Sonnet-20250219 (Prompt),65.79%,83.64%,87.98%,83.57%,68.75%,50.00%,37.76%,100.00%
78+
77,FireFunction-v2 (FC),65.66%,78.09%,79.07%,78.35%,56.25%,70.83%,46.03%,94.44%
79+
78,Qwen3-0.6B (FC),65.66%,56.40%,65.89%,54.42%,37.50%,54.17%,79.82%,66.67%
8080
79,GPT-4.1-nano-2025-04-14 (Prompt),65.35%,60.77%,65.12%,58.97%,81.25%,79.17%,72.22%,72.22%
8181
80,Ministral-8B-Instruct-2410 (FC),64.93%,72.61%,75.58%,72.27%,62.50%,62.50%,53.06%,70.59%
82-
81,Qwen2.5-1.5B-Instruct (FC),64.82%,67.06%,74.03%,66.10%,50.00%,45.83%,60.77%,94.44%
83-
82,GPT-4.1-nano-2025-04-14 (FC),64.33%,72.17%,65.50%,73.41%,87.50%,79.17%,51.70%,94.44%
84-
83,Hammer2.1-0.5b (FC),62.91%,58.11%,60.08%,58.02%,50.00%,45.83%,69.95%,77.78%
85-
84,Llama-3.3-70B-Instruct (FC),62.67%,78.02%,81.78%,77.11%,93.75%,66.67%,38.44%,100.00%
86-
85,Llama-3.1-70B-Instruct (Prompt),62.24%,76.54%,78.29%,76.16%,87.50%,66.67%,39.57%,100.00%
87-
86,Phi-4-mini-instruct (FC),61.47%,47.45%,40.31%,50.33%,0.00%,29.17%,82.88%,64.71%
88-
87,Qwen2.5-1.5B-Instruct (Prompt),61.08%,61.07%,70.54%,59.26%,56.25%,41.67%,60.66%,83.33%
89-
88,Llama-3.1-8B-Instruct (Prompt),61.08%,72.91%,74.03%,73.31%,56.25%,54.17%,42.63%,77.78%
90-
89,Llama-4-Maverick-17B-128E-Instruct-FP8 (Prompt) (Novita),60.77%,77.57%,84.11%,75.97%,81.25%,75.00%,34.24%,100.00%
91-
90,DBRX-Instruct (Prompt),60.28%,73.50%,78.29%,73.03%,75.00%,41.67%,39.34%,94.44%
92-
91,Llama-4-Maverick-17B-128E-Instruct-FP8 (FC) (Novita),60.02%,64.69%,74.42%,64.77%,0.00%,0.00%,52.49%,77.78%
93-
92,Granite-20b-FunctionCalling (FC),59.66%,58.48%,68.22%,56.32%,43.75%,58.33%,60.88%,88.89%
94-
93,Gemma-3-4b-it (Prompt),59.17%,63.80%,72.87%,62.77%,37.50%,29.17%,51.70%,77.78%
95-
94,xLAM-2-1b-fc-r (FC),59.17%,62.62%,74.03%,60.68%,50.00%,33.33%,53.17%,94.44%
96-
95,Command-R-Plus (FC),59.00%,60.84%,70.54%,58.78%,62.50%,45.83%,55.90%,72.22%
97-
96,xLAM-2-3b-fc-r (FC),58.91%,64.32%,74.42%,62.11%,68.75%,50.00%,50.00%,88.89%
98-
97,Bielik-11B-v2.3-Instruct (Prompt),58.91%,69.43%,72.87%,69.33%,43.75%,54.17%,42.40%,77.78%
99-
98,Qwen2.5-3B-Instruct (Prompt),58.69%,66.91%,69.77%,66.48%,56.25%,62.50%,45.46%,88.89%
100-
99,Llama-4-Maverick-17B-128E-Instruct-FP8 (FC),58.55%,76.17%,83.33%,74.64%,81.25%,62.50%,30.73%,100.00%
101-
100,Llama-4-Scout-17B-16E-Instruct (FC),57.97%,74.76%,77.91%,74.36%,68.75%,62.50%,31.41%,100.00%
102-
101,Llama-3.2-3B-Instruct (FC),55.80%,63.73%,63.95%,64.86%,12.50%,45.83%,42.97%,88.89%
103-
102,Falcon3-7B-Instruct (FC),54.86%,67.95%,74.03%,66.48%,75.00%,62.50%,34.13%,88.89%
104-
103,MiniCPM3-4B (Prompt),54.46%,37.23%,46.51%,34.76%,43.75%,41.67%,80.95%,50.00%
105-
104,Nexusflow-Raven-v2 (FC),54.20%,39.45%,41.47%,38.65%,56.25%,41.67%,76.64%,61.11%
106-
105,Falcon3-10B-Instruct (FC),54.11%,75.28%,76.36%,76.16%,50.00%,41.67%,20.86%,94.44%
107-
106,Llama-4-Scout-17B-16E-Instruct (Prompt) (Novita),52.11%,70.32%,75.97%,69.52%,62.50%,50.00%,23.24%,100.00%
108-
107,Phi-4-mini-instruct (Prompt),50.62%,58.85%,55.04%,59.45%,68.75%,66.67%,37.41%,82.35%
109-
108,Open-Mistral-Nemo-2407 (Prompt),49.04%,75.13%,77.91%,74.45%,87.50%,66.67%,8.28%,88.89%
110-
109,Qwen2.5-0.5B-Instruct (FC),47.98%,43.97%,56.20%,41.31%,56.25%,20.83%,53.29%,88.89%
111-
110,Falcon3-3B-Instruct (FC),47.40%,55.51%,55.43%,56.32%,31.25%,37.50%,34.35%,77.78%
112-
111,Llama-3.1-70B-Instruct (FC),45.00%,51.81%,52.33%,52.61%,31.25%,25.00%,33.45%,100.00%
113-
112,Llama-4-Scout-17B-16E-Instruct (FC) (Novita),41.09%,46.71%,59.69%,45.20%,0.00%,4.17%,31.52%,88.89%
114-
113,QwQ-32B-Preview (Prompt),40.78%,3.55%,7.36%,2.75%,0.00%,0.00%,98.64%,0.00%
115-
114,Qwen/QwQ-32B (Prompt) (Novita),39.18%,0.00%,0.00%,0.00%,0.00%,0.00%,100.00%,0.00%
116-
115,Llama-3.1-8B-Instruct (FC),33.50%,49.30%,51.94%,49.00%,37.50%,41.67%,8.05%,94.44%
117-
116,Falcon3-1B-Instruct (FC),32.70%,2.96%,4.65%,2.37%,0.00%,12.50%,78.91%,0.00%
118-
117,Qwen2.5-0.5B-Instruct (Prompt),31.59%,38.34%,53.88%,34.76%,56.25%,16.67%,19.95%,94.44%
119-
118,Llama-3.2-1B-Instruct (FC),31.36%,12.14%,31.40%,7.60%,12.50%,4.17%,60.66%,38.89%
120-
119,Gemma-3-1b-it (Prompt),30.34%,14.14%,31.01%,10.54%,0.00%,0.00%,54.76%,50.00%
121-
120,ThinkAgent-1B (FC),25.37%,17.62%,24.42%,16.43%,6.25%,4.17%,36.85%,44.44%
122-
121,Grok-3-mini-beta (Prompt),0.00%,N/A,N/A,N/A,N/A,N/A,N/A,N/A
82+
81,GPT-4.1-nano-2025-04-14 (FC),64.33%,72.17%,65.50%,73.41%,87.50%,79.17%,51.70%,94.44%
83+
82,Hammer2.1-0.5b (FC),62.91%,58.11%,60.08%,58.02%,50.00%,45.83%,69.95%,77.78%
84+
83,Llama-3.3-70B-Instruct (FC),62.67%,78.02%,81.78%,77.11%,93.75%,66.67%,38.44%,100.00%
85+
84,Llama-3.1-70B-Instruct (Prompt),62.24%,76.54%,78.29%,76.16%,87.50%,66.67%,39.57%,100.00%
86+
85,Phi-4-mini-instruct (FC),61.47%,47.45%,40.31%,50.33%,0.00%,29.17%,82.88%,64.71%
87+
86,Llama-3.1-8B-Instruct (Prompt),61.08%,72.91%,74.03%,73.31%,56.25%,54.17%,42.63%,77.78%
88+
87,DBRX-Instruct (Prompt),60.28%,73.50%,78.29%,73.03%,75.00%,41.67%,39.34%,94.44%
89+
88,Granite-20b-FunctionCalling (FC),59.66%,58.48%,68.22%,56.32%,43.75%,58.33%,60.88%,88.89%
90+
89,Gemma-3-4b-it (Prompt),59.17%,63.80%,72.87%,62.77%,37.50%,29.17%,51.70%,77.78%
91+
90,xLAM-2-1b-fc-r (FC),59.17%,62.62%,74.03%,60.68%,50.00%,33.33%,53.17%,94.44%
92+
91,Command-R-Plus (FC),59.00%,60.84%,70.54%,58.78%,62.50%,45.83%,55.90%,72.22%
93+
92,xLAM-2-3b-fc-r (FC),58.91%,64.32%,74.42%,62.11%,68.75%,50.00%,50.00%,88.89%
94+
93,Bielik-11B-v2.3-Instruct (Prompt),58.91%,69.43%,72.87%,69.33%,43.75%,54.17%,42.40%,77.78%
95+
94,Llama-4-Maverick-17B-128E-Instruct-FP8 (FC),58.55%,76.17%,83.33%,74.64%,81.25%,62.50%,30.73%,100.00%
96+
95,Llama-4-Scout-17B-16E-Instruct (FC),57.97%,74.76%,77.91%,74.36%,68.75%,62.50%,31.41%,100.00%
97+
96,Llama-3.2-3B-Instruct (FC),55.80%,63.73%,63.95%,64.86%,12.50%,45.83%,42.97%,88.89%
98+
97,Falcon3-7B-Instruct (FC),54.86%,67.95%,74.03%,66.48%,75.00%,62.50%,34.13%,88.89%
99+
98,MiniCPM3-4B (Prompt),54.46%,37.23%,46.51%,34.76%,43.75%,41.67%,80.95%,50.00%
100+
99,Nexusflow-Raven-v2 (FC),54.20%,39.45%,41.47%,38.65%,56.25%,41.67%,76.64%,61.11%
101+
100,Falcon3-10B-Instruct (FC),54.11%,75.28%,76.36%,76.16%,50.00%,41.67%,20.86%,94.44%
102+
101,Phi-4-mini-instruct (Prompt),50.62%,58.85%,55.04%,59.45%,68.75%,66.67%,37.41%,82.35%
103+
102,Open-Mistral-Nemo-2407 (Prompt),49.04%,75.13%,77.91%,74.45%,87.50%,66.67%,8.28%,88.89%
104+
103,Falcon3-3B-Instruct (FC),47.40%,55.51%,55.43%,56.32%,31.25%,37.50%,34.35%,77.78%
105+
104,Llama-3.1-70B-Instruct (FC),45.00%,51.81%,52.33%,52.61%,31.25%,25.00%,33.45%,100.00%
106+
105,Llama-3.1-8B-Instruct (FC),33.50%,49.30%,51.94%,49.00%,37.50%,41.67%,8.05%,94.44%
107+
106,Falcon3-1B-Instruct (FC),32.70%,2.96%,4.65%,2.37%,0.00%,12.50%,78.91%,0.00%
108+
107,Llama-3.2-1B-Instruct (FC),31.36%,12.14%,31.40%,7.60%,12.50%,4.17%,60.66%,38.89%
109+
108,Gemma-3-1b-it (Prompt),30.34%,14.14%,31.01%,10.54%,0.00%,0.00%,54.76%,50.00%
110+
109,ThinkAgent-1B (FC),25.37%,17.62%,24.42%,16.43%,6.25%,4.17%,36.85%,44.44%

0 commit comments

Comments
 (0)