Hugging Face's logo

open-agent-leaderboard
/
openai-solo

agent
agent-evaluation
agent-card
Eval Results
Model card Files
xet
 Community
Elron commited on
Commit
ba6bb61
·
verified ·
1 Parent(s): e4166d2

Add Open Agent Leaderboard evaluation results

Browse files

Results from the Open Agent Leaderboard (https://www.exgentic.ai), evaluating this agent across 6 benchmarks with 5 different models.

Files changed (5) hide show
  1. .eval_results/open_agent_leaderboard_openai_aws_claude-opus-4-5.yaml +56 -0
  2. .eval_results/open_agent_leaderboard_openai_azure_deepseek-v3.2.yaml +56 -0
  3. .eval_results/open_agent_leaderboard_openai_azure_gpt-5.2-2025-12-11.yaml +56 -0
  4. .eval_results/open_agent_leaderboard_openai_azure_kimi-k2.5.yaml +56 -0
  5. .eval_results/open_agent_leaderboard_openai_gcp_gemini-3-pro-preview.yaml +56 -0
.eval_results/open_agent_leaderboard_openai_aws_claude-opus-4-5.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: open-agent-leaderboard/results
3
+ task_id: overall
4
+ value: 0.7268
5
+ source:
6
+ url: https://www.exgentic.ai
7
+ name: Open Agent Leaderboard
8
+ notes: 'model: Claude Opus 4.5'
9
+ - dataset:
10
+ id: open-agent-leaderboard/results
11
+ task_id: appworld
12
+ value: 0.68
13
+ source:
14
+ url: https://www.exgentic.ai
15
+ name: Open Agent Leaderboard
16
+ notes: 'model: Claude Opus 4.5'
17
+ - dataset:
18
+ id: open-agent-leaderboard/results
19
+ task_id: browsecomp_plus
20
+ value: 0.61
21
+ source:
22
+ url: https://www.exgentic.ai
23
+ name: Open Agent Leaderboard
24
+ notes: 'model: Claude Opus 4.5'
25
+ - dataset:
26
+ id: open-agent-leaderboard/results
27
+ task_id: swebench
28
+ value: 0.8072
29
+ source:
30
+ url: https://www.exgentic.ai
31
+ name: Open Agent Leaderboard
32
+ notes: 'model: Claude Opus 4.5'
33
+ - dataset:
34
+ id: open-agent-leaderboard/results
35
+ task_id: taubench_airline
36
+ value: 0.74
37
+ source:
38
+ url: https://www.exgentic.ai
39
+ name: Open Agent Leaderboard
40
+ notes: 'model: Claude Opus 4.5'
41
+ - dataset:
42
+ id: open-agent-leaderboard/results
43
+ task_id: taubench_retail
44
+ value: 0.85
45
+ source:
46
+ url: https://www.exgentic.ai
47
+ name: Open Agent Leaderboard
48
+ notes: 'model: Claude Opus 4.5'
49
+ - dataset:
50
+ id: open-agent-leaderboard/results
51
+ task_id: taubench_telecom
52
+ value: 0.84
53
+ source:
54
+ url: https://www.exgentic.ai
55
+ name: Open Agent Leaderboard
56
+ notes: 'model: Claude Opus 4.5'
.eval_results/open_agent_leaderboard_openai_azure_deepseek-v3.2.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: open-agent-leaderboard/results
3
+ task_id: overall
4
+ value: 0.3217
5
+ source:
6
+ url: https://www.exgentic.ai
7
+ name: Open Agent Leaderboard
8
+ notes: 'model: DeepSeek V3.2'
9
+ - dataset:
10
+ id: open-agent-leaderboard/results
11
+ task_id: appworld
12
+ value: 0.06
13
+ source:
14
+ url: https://www.exgentic.ai
15
+ name: Open Agent Leaderboard
16
+ notes: 'model: DeepSeek V3.2'
17
+ - dataset:
18
+ id: open-agent-leaderboard/results
19
+ task_id: browsecomp_plus
20
+ value: 0.3
21
+ source:
22
+ url: https://www.exgentic.ai
23
+ name: Open Agent Leaderboard
24
+ notes: 'model: DeepSeek V3.2'
25
+ - dataset:
26
+ id: open-agent-leaderboard/results
27
+ task_id: swebench
28
+ value: 0.7368
29
+ source:
30
+ url: https://www.exgentic.ai
31
+ name: Open Agent Leaderboard
32
+ notes: 'model: DeepSeek V3.2'
33
+ - dataset:
34
+ id: open-agent-leaderboard/results
35
+ task_id: taubench_airline
36
+ value: 0.2
37
+ source:
38
+ url: https://www.exgentic.ai
39
+ name: Open Agent Leaderboard
40
+ notes: 'model: DeepSeek V3.2'
41
+ - dataset:
42
+ id: open-agent-leaderboard/results
43
+ task_id: taubench_retail
44
+ value: 0.19
45
+ source:
46
+ url: https://www.exgentic.ai
47
+ name: Open Agent Leaderboard
48
+ notes: 'model: DeepSeek V3.2'
49
+ - dataset:
50
+ id: open-agent-leaderboard/results
51
+ task_id: taubench_telecom
52
+ value: 0.18
53
+ source:
54
+ url: https://www.exgentic.ai
55
+ name: Open Agent Leaderboard
56
+ notes: 'model: DeepSeek V3.2'
.eval_results/open_agent_leaderboard_openai_azure_gpt-5.2-2025-12-11.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: open-agent-leaderboard/results
3
+ task_id: overall
4
+ value: 0.3864
5
+ source:
6
+ url: https://www.exgentic.ai
7
+ name: Open Agent Leaderboard
8
+ notes: 'model: GPT-5.2'
9
+ - dataset:
10
+ id: open-agent-leaderboard/results
11
+ task_id: appworld
12
+ value: 0.0
13
+ source:
14
+ url: https://www.exgentic.ai
15
+ name: Open Agent Leaderboard
16
+ notes: 'model: GPT-5.2'
17
+ - dataset:
18
+ id: open-agent-leaderboard/results
19
+ task_id: browsecomp_plus
20
+ value: 0.48
21
+ source:
22
+ url: https://www.exgentic.ai
23
+ name: Open Agent Leaderboard
24
+ notes: 'model: GPT-5.2'
25
+ - dataset:
26
+ id: open-agent-leaderboard/results
27
+ task_id: swebench
28
+ value: 0.5455
29
+ source:
30
+ url: https://www.exgentic.ai
31
+ name: Open Agent Leaderboard
32
+ notes: 'model: GPT-5.2'
33
+ - dataset:
34
+ id: open-agent-leaderboard/results
35
+ task_id: taubench_airline
36
+ value: 0.5
37
+ source:
38
+ url: https://www.exgentic.ai
39
+ name: Open Agent Leaderboard
40
+ notes: 'model: GPT-5.2'
41
+ - dataset:
42
+ id: open-agent-leaderboard/results
43
+ task_id: taubench_retail
44
+ value: 0.53
45
+ source:
46
+ url: https://www.exgentic.ai
47
+ name: Open Agent Leaderboard
48
+ notes: 'model: GPT-5.2'
49
+ - dataset:
50
+ id: open-agent-leaderboard/results
51
+ task_id: taubench_telecom
52
+ value: 0.53
53
+ source:
54
+ url: https://www.exgentic.ai
55
+ name: Open Agent Leaderboard
56
+ notes: 'model: GPT-5.2'
.eval_results/open_agent_leaderboard_openai_azure_kimi-k2.5.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: open-agent-leaderboard/results
3
+ task_id: overall
4
+ value: 0.2501
5
+ source:
6
+ url: https://www.exgentic.ai
7
+ name: Open Agent Leaderboard
8
+ notes: 'model: Kimi K2.5'
9
+ - dataset:
10
+ id: open-agent-leaderboard/results
11
+ task_id: appworld
12
+ value: 0.08
13
+ source:
14
+ url: https://www.exgentic.ai
15
+ name: Open Agent Leaderboard
16
+ notes: 'model: Kimi K2.5'
17
+ - dataset:
18
+ id: open-agent-leaderboard/results
19
+ task_id: browsecomp_plus
20
+ value: 0.35
21
+ source:
22
+ url: https://www.exgentic.ai
23
+ name: Open Agent Leaderboard
24
+ notes: 'model: Kimi K2.5'
25
+ - dataset:
26
+ id: open-agent-leaderboard/results
27
+ task_id: swebench
28
+ value: 0.567
29
+ source:
30
+ url: https://www.exgentic.ai
31
+ name: Open Agent Leaderboard
32
+ notes: 'model: Kimi K2.5'
33
+ - dataset:
34
+ id: open-agent-leaderboard/results
35
+ task_id: taubench_airline
36
+ value: 0.0
37
+ source:
38
+ url: https://www.exgentic.ai
39
+ name: Open Agent Leaderboard
40
+ notes: 'model: Kimi K2.5'
41
+ - dataset:
42
+ id: open-agent-leaderboard/results
43
+ task_id: taubench_retail
44
+ value: 0.01
45
+ source:
46
+ url: https://www.exgentic.ai
47
+ name: Open Agent Leaderboard
48
+ notes: 'model: Kimi K2.5'
49
+ - dataset:
50
+ id: open-agent-leaderboard/results
51
+ task_id: taubench_telecom
52
+ value: 0.0
53
+ source:
54
+ url: https://www.exgentic.ai
55
+ name: Open Agent Leaderboard
56
+ notes: 'model: Kimi K2.5'
.eval_results/open_agent_leaderboard_openai_gcp_gemini-3-pro-preview.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: open-agent-leaderboard/results
3
+ task_id: overall
4
+ value: 0.585
5
+ source:
6
+ url: https://www.exgentic.ai
7
+ name: Open Agent Leaderboard
8
+ notes: 'model: Gemini 3 Pro'
9
+ - dataset:
10
+ id: open-agent-leaderboard/results
11
+ task_id: appworld
12
+ value: 0.57
13
+ source:
14
+ url: https://www.exgentic.ai
15
+ name: Open Agent Leaderboard
16
+ notes: 'model: Gemini 3 Pro'
17
+ - dataset:
18
+ id: open-agent-leaderboard/results
19
+ task_id: browsecomp_plus
20
+ value: 0.3333
21
+ source:
22
+ url: https://www.exgentic.ai
23
+ name: Open Agent Leaderboard
24
+ notes: 'model: Gemini 3 Pro'
25
+ - dataset:
26
+ id: open-agent-leaderboard/results
27
+ task_id: swebench
28
+ value: 0.7234
29
+ source:
30
+ url: https://www.exgentic.ai
31
+ name: Open Agent Leaderboard
32
+ notes: 'model: Gemini 3 Pro'
33
+ - dataset:
34
+ id: open-agent-leaderboard/results
35
+ task_id: taubench_airline
36
+ value: 0.62
37
+ source:
38
+ url: https://www.exgentic.ai
39
+ name: Open Agent Leaderboard
40
+ notes: 'model: Gemini 3 Pro'
41
+ - dataset:
42
+ id: open-agent-leaderboard/results
43
+ task_id: taubench_retail
44
+ value: 0.73
45
+ source:
46
+ url: https://www.exgentic.ai
47
+ name: Open Agent Leaderboard
48
+ notes: 'model: Gemini 3 Pro'
49
+ - dataset:
50
+ id: open-agent-leaderboard/results
51
+ task_id: taubench_telecom
52
+ value: 0.79
53
+ source:
54
+ url: https://www.exgentic.ai
55
+ name: Open Agent Leaderboard
56
+ notes: 'model: Gemini 3 Pro'