Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Use on LiveMCPBench
Loading...
77
LiveMCP Score
GEPA
-3.08
17.71
38.5
59.29
Jul 5, 2026
LiveMCP Score
Updated 18d ago
Evaluation Results
Method
Method
Links
LiveMCP Score
GEPA
Model=Kimi-k2.6
2026.07
77
NRE
Model=gpt-oss-120b
2026.07
76
NRE
Model=Mistral 3.5
2026.07
75
NRE
Model=gpt-5.4-mini
2026.07
75
Vanilla
Model=Opus 4.7
2026.07
75
NRE
Model=Kimi-k2.6
2026.07
74.7
Vanilla
Model=Sonnet 4.6
2026.07
74.7
NRE
Model=Deepseek-v3
2026.07
73.7
Vanilla
Model=Kimi-k2.6
2026.07
72
Vanilla
Model=Haiku 4.5
2026.07
70.5
NRE
Model=Haiku 4.5
2026.07
69
GEPA
Model=gpt-oss-120b
2026.07
63.2
Vanilla
Model=Deepseek-v3
2026.07
54
Vanilla
Model=gpt-oss-120b
2026.07
53
Vanilla
Model=Deepseek-R1
2026.07
43
Vanilla
Model=gpt-5.4-mini
2026.07
42
GEPA
Model=Deepseek-v3
2026.07
40
RLM
Model=Kimi-k2.6
2026.07
14.7
RLM
Model=gpt-oss-120b
2026.07
5.3
RLM
Model=Deepseek-v3
2026.07
0
Feedback
Search any
task
Search any
task