Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
AgentWorldBench MCP
general_agent
|
83.52%
|
24.06.2026 |
#6/14
better than 62%
|
|
AgentWorldBench Search
general_agent
|
3.27%
|
24.06.2026 |
#13/14
better than 8%
|
|
AgentWorldBench Terminal
general_agent
|
32.46%
|
24.06.2026 |
#12/14
better than 15%
|
|
AgentWorldBench SWE
general_agent
|
47.12%
|
24.06.2026 |
#12/14
better than 15%
|
|
AgentWorldBench Android
general_agent
|
71.73%
|
24.06.2026 |
#6/14
better than 62%
|
|
AgentWorldBench Web
general_agent
|
58.20%
|
24.06.2026 |
#4/14
better than 77%
|
|
AgentWorldBench OS
general_agent
|
20.53%
|
24.06.2026 |
#12/14
better than 15%
|
|
AgentWorldBench Overall
general_agent
|
41.22%
|
24.06.2026 |
#11/14
better than 23%
|
|
BrowseComp
general_agent
|
63.26%
|
04.06.2026 |
#25/45
better than 43%
|
|
Vals.ai Financial Agent 1.1 (without web search)
general_agent
|
89.00%
|
04.06.2026 |
#2/7
better than 83%
|
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
56.49%
|
04.06.2026 |
#27/44
better than 40%
|
|
CritPt (no tools)
stem_reasoning
|
9.78%
|
04.06.2026 |
#17/21
better than 15%
|
|
Vals.ai Financial Agent 1.1 (with web search)
general_agent
|
86.44%
|
04.06.2026 |
#2/7
better than 83%
|
|
GDPVal
general_agent
|
40.04%
|
04.06.2026 |
#14/20
better than 32%
|
|
MMLU-Pro
knowledge
|
83.55%
|
04.06.2026 |
#15/48
better than 70%
|
|
IOI 2025
stem_reasoning
|
10.58%
|
04.06.2026 |
#4/5
better than 25%
|
|
LiveCodeBench v6
stem_reasoning
|
89.36%
|
04.06.2026 |
#17/49
better than 67%
|
|
SWE-bench Verified
coding_agent
|
86.93%
|
04.06.2026 |
#19/60
better than 68%
|
|
SWE-bench Multilingual
coding_agent
|
82.60%
|
04.06.2026 |
#18/48
better than 64%
|
|
IMOAnswerBench
stem_reasoning
|
91.19%
|
04.06.2026 |
#9/30
better than 72%
|
|
ProfBench (Search)
general_agent
|
46.00
|
04.06.2026 |
#7/7
better than 0%
|
|
Apex-Shortlist (no tools)
stem_reasoning
|
68.84%
|
04.06.2026 |
#9/11
better than 20%
|
|
OmniScience Non-Hallucination
knowledge
|
71.01%
|
04.06.2026 |
#5/10
better than 56%
|
|
IFBench (prompt loose)
instruction_following
|
72.31%
|
04.06.2026 |
#9/14
better than 38%
|
|
PinchBench
general_agent
|
26.28%
|
04.06.2026 |
#8/9
better than 12%
|
|
TauBench V3 Airline
general_agent
|
92.38%
|
04.06.2026 |
#2/7
better than 83%
|
|
Multi-Challenge
instruction_following
|
94.91%
|
04.06.2026 |
#8/18
better than 59%
|
|
TauBench V3 Retail
general_agent
|
19.35%
|
04.06.2026 |
#6/7
better than 17%
|
|
TauBench V3 Telecom
general_agent
|
83.91%
|
04.06.2026 |
#4/7
better than 50%
|
|
GPQA Diamond
stem_reasoning
|
84.50%
|
04.06.2026 |
#46/80
better than 43%
|
|
AA-LCR
long_context
|
79.64%
|
04.06.2026 |
#20/42
better than 51%
|
|
SciCode (subtask)
stem_reasoning
|
45.63%
|
04.06.2026 |
#10/15
better than 36%
|
|
Humanity's Last Exam
stem_reasoning
|
47.54%
|
04.06.2026 |
#36/71
better than 50%
|
|
MMLU-ProX
multilingual
|
96.13%
|
04.06.2026 |
#2/19
better than 94%
|
|
TauBench V3 Average
general_agent
|
47.37%
|
04.06.2026 |
#6/7
better than 17%
|
|
WMT24++ (en→xx)
multilingual
|
95.21%
|
04.06.2026 |
#5/17
better than 75%
|
|
AIME 26
stem_reasoning
|
95.03%
|
17.06.2026 |
#17/45
better than 64%
|
|
HMMT Nov 25
stem_reasoning
|
87.31%
|
17.06.2026 |
#7/20
better than 68%
|
|
HMMT Feb 26
stem_reasoning
|
80.44%
|
17.06.2026 |
#26/44
better than 42%
|
|
SWE-bench Pro
coding_agent
|
65.11%
|
17.06.2026 |
#23/77
better than 70%
|
|
NL2Repo
coding_agent
|
49.85%
|
17.06.2026 |
#21/41
better than 50%
|
|
ProgramBench
coding_agent
|
69.52%
|
17.06.2026 |
#4/18
better than 82%
|
|
Terminal-Bench 2.1 (Best Reported Harness)
coding_agent
|
69.00
|
17.06.2026 |
#5/5
better than 0%
|
|
FrontierSWE
coding_agent
|
2.53%
|
17.06.2026 |
#11/12
better than 9%
|
|
PostTrainBench
coding_agent
|
23.89%
|
17.06.2026 |
#19/22
better than 14%
|
|
SWE-Marathon
coding_agent
|
1.00
|
17.06.2026 |
#17/17
better than 0%
|
|
MCP-Atlas
general_agent
|
77.28%
|
17.06.2026 |
#25/54
better than 53%
|
|
Tool Decathlon
general_agent
|
59.92%
|
17.06.2026 |
#6/11
better than 50%
|
|
HLE (with tools)
stem_reasoning
|
65.06%
|
04.06.2026 |
#28/49
better than 44%
|
|
Apex-Agents
general_agent
|
9.19%
|
26.06.2026 |
#22/24
better than 4%
|
|
Terminal-Bench 2.0
coding_agent
|
86.34%
|
26.06.2026 |
#7/23
better than 73%
|
|
GDPVal-AA v2
general_agent
|
83.83%
|
26.06.2026 |
#18/38
better than 54%
|
|
Toolathlon Verified
general_agent
|
25.75%
|
26.06.2026 |
#33/35
better than 6%
|
|
Apex-Shortlist (with tools)
stem_reasoning
|
78.32%
|
04.06.2026 |
#4/7
better than 50%
|
|
IMOAnswerBench (with tools)
stem_reasoning
|
85.98%
|
04.06.2026 |
#3/7
better than 67%
|
|
TauBench V3 Banking
general_agent
|
15.83%
|
04.06.2026 |
#16/17
better than 6%
|
|
DeepSWE 1.1
coding_agent
|
23.18%
|
17.06.2026 |
#27/34
better than 18%
|
|
OmniScience Accuracy
knowledge
|
60.99%
|
04.06.2026 |
#5/10
better than 56%
|
What is a good AgentWorldBench MCP score? What is a good AgentWorldBench Search score? What is a good AgentWorldBench Terminal score?
Trend Analysis
24h Change
+0.2%
7d Change
+1.1%
30d Change
+6.0%
Current
23,389
huggingface
downloads_all_time
+0.4%
huggingface
downloads
-3.2%
huggingface
likes
+0.0%
No comments yet
Be the first to share your thoughts!