Skip to content

Benchmark

Galileo Agent Leaderboard

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.

Models measured
21
Scores recorded
126
Sources
1
IQ weight
1.15

Score distribution

40.7%
Mean
42%
Median
14.8%
Std dev
18%
10th percentile
60%
90th percentile
11%
Min
11%74%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.15 for chat models, measured over 21 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Nova Prov1· Galileo Agent Leaderboard data29%
102Mistral SmallHealthcare, 2506· Galileo Agent Leaderboard data28%
103Magistral MediumInvestment, 2506· Galileo Agent Leaderboard data26%
104Mistral Small2506· Galileo Agent Leaderboard data26%
105Magistral Small 2509Banking, 2506· Galileo Agent Leaderboard data23%
106Qwen 3 235B A22B Thinking 2507Investment· Galileo Agent Leaderboard data23%
107Gemini 2.5 FlashInvestment· Galileo Agent Leaderboard data22%
108Mistral SmallInsurance, 2506· Galileo Agent Leaderboard data22%
109Mistral SmallTelecom, 2506· Galileo Agent Leaderboard data21%
110Llama 3.3 70B Instruct· Galileo Agent Leaderboard data20%
111Mistral SmallInvestment, 2506· Galileo Agent Leaderboard data20%
112Nova LiteInsurance, v1· Galileo Agent Leaderboard data19%
113Magistral Small 2509Healthcare, 2506· Galileo Agent Leaderboard data18%
114Nova LiteHealthcare, v1· Galileo Agent Leaderboard data18%
115Nova LiteTelecom, v1· Galileo Agent Leaderboard data18%
116Nova ProInvestment, v1· Galileo Agent Leaderboard data17%
117Llama 3.3 70B InstructTelecom· Galileo Agent Leaderboard data16%
118Magistral Small 25092506· Galileo Agent Leaderboard data16%
119Magistral Small 2509Investment, 2506· Galileo Agent Leaderboard data16%
120Nova Litev1· Galileo Agent Leaderboard data16%
121Nova LiteInvestment, v1· Galileo Agent Leaderboard data15%
122Llama 3.3 70B InstructInvestment· Galileo Agent Leaderboard data14%
123Magistral Small 2509Insurance, 2506· Galileo Agent Leaderboard data13%
124Magistral Small 2509Telecom, 2506· Galileo Agent Leaderboard data12%
125Nova LiteBanking, v1· Galileo Agent Leaderboard data12%
126Llama 3.3 70B InstructBanking· Galileo Agent Leaderboard data11%

Showing 101–126 of 126 results.

Data credits: Galileo Agent Leaderboard, Apache-2.0 (licence)