AI Model Leaderboard

Agentic work ranking, Model families, sorted by Overall
Rank Model Provider Weights Overall Coding Agents Reasoning Math Knowledge Cost
11 Muse Wonder Meta 62.8 62.9 62.4 63.8 62.8 63.2 $8.00
12 Muse Wonder Full Meta 62.6 61.0 62.8 64.7 64.1 64.3 –No price
19 Muse Ember New Meta 61.9 –No results 62.0 61.7 –No results 62.7 $0.20
21 Muse Spark 1.3 Meta 60.9 61.3 60.1 63.2 60.5 65.0 $0.13
55 Muse Spark 1.1 Meta 58.0 58.3 57.4 60.2 56.8 58.8 $2.00
57 Muse Spark 1.2 Meta 57.9 57.6 57.5 60.1 57.4 59.4 $2.00