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
51GPT-4.1 miniInsurance· Galileo Agent Leaderboard data46%
52Gemini 2.5 Flash-LiteBanking· Galileo Agent Leaderboard data45%
53Gemini 2.5 ProBanking· Galileo Agent Leaderboard data45%
54Gemini 2.5 FlashInsurance· Galileo Agent Leaderboard data44%
55Gemini 2.5 ProTelecom· Galileo Agent Leaderboard data44%
56GLM 4.5 Air· Galileo Agent Leaderboard data44%
57Qwen3 235B A22B Instruct 2507Banking· Galileo Agent Leaderboard data44%
58Gemini 2.5 Pro· Galileo Agent Leaderboard data43%
59Grok 4· Galileo Agent Leaderboard data42%
60Grok 4Telecom· Galileo Agent Leaderboard data42%
61Qwen 3 235B A22B Thinking 2507Banking· Galileo Agent Leaderboard data42%
62Qwen 3 235B A22B Thinking 2507Insurance· Galileo Agent Leaderboard data42%
63Qwen2.5 72B InstructInvestment· Galileo Agent Leaderboard data42%
64Gemini 2.5 Flash-LiteTelecom· Galileo Agent Leaderboard data41%
65GPT-4.1 nanoInsurance· Galileo Agent Leaderboard data41%
66Qwen3 235B A22B Instruct 2507Investment· Galileo Agent Leaderboard data41%
67DeepSeek V3· Galileo Agent Leaderboard data40%
68Gemini 2.5 ProHealthcare· Galileo Agent Leaderboard data40%
69GLM 4.5 AirHealthcare· Galileo Agent Leaderboard data40%
70GPT-4.1 nanoBanking· Galileo Agent Leaderboard data40%
71GPT-4.1 nanoHealthcare· Galileo Agent Leaderboard data40%
72Grok 4Healthcare· Galileo Agent Leaderboard data40%
73Nova ProInsurance, v1· Galileo Agent Leaderboard data39%
74DeepSeek V3Banking· Galileo Agent Leaderboard data38%
75Gemini 2.5 Flash· Galileo Agent Leaderboard data38%
76Gemini 2.5 FlashHealthcare· Galileo Agent Leaderboard data38%
77GPT-4.1 nano· Galileo Agent Leaderboard data38%
78GPT-4.1 nanoTelecom· Galileo Agent Leaderboard data38%
79Magistral MediumInsurance, 2506· Galileo Agent Leaderboard data38%
80Mistral SmallBanking, 2506· Galileo Agent Leaderboard data37%
81DeepSeek V3Investment· Galileo Agent Leaderboard data36%
82Gemini 2.5 FlashTelecom· Galileo Agent Leaderboard data36%
83Gemini 2.5 Flash-LiteInvestment· Galileo Agent Leaderboard data35%
84Magistral MediumHealthcare, 2506· Galileo Agent Leaderboard data35%
85Qwen 3 235B A22B Thinking 2507· Galileo Agent Leaderboard data34%
86Qwen 3 235B A22B Thinking 2507Telecom· Galileo Agent Leaderboard data34%
87GLM 4.5 AirTelecom· Galileo Agent Leaderboard data33%
88Nova ProBanking, v1· Galileo Agent Leaderboard data33%
89DeepSeek V3Healthcare· Galileo Agent Leaderboard data32%
90Magistral Medium2506· Galileo Agent Leaderboard data32%
91Gemini 2.5 ProInvestment· Galileo Agent Leaderboard data31%
92Magistral MediumBanking, 2506· Galileo Agent Leaderboard data30%
93Magistral MediumTelecom, 2506· Galileo Agent Leaderboard data30%
94Qwen 3 235B A22B Thinking 2507Healthcare· Galileo Agent Leaderboard data30%
95GPT-4.1 nanoInvestment· Galileo Agent Leaderboard data29%
96Grok 4Banking· Galileo Agent Leaderboard data29%
97Llama 3.3 70B InstructHealthcare· Galileo Agent Leaderboard data29%
98Llama 3.3 70B InstructInsurance· Galileo Agent Leaderboard data29%
99Nova ProHealthcare, v1· Galileo Agent Leaderboard data29%
100Nova ProTelecom, v1· Galileo Agent Leaderboard data29%

Showing 51–100 of 126 results.

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