AI Model Leaderboard

Reasoning ranking, Model families, sorted by Overall
Rank Model Provider Weights Overall Coding Agents Reasoning Math Knowledge Cost
11 Muse Wonder Full Meta 64.4 61.0 62.8 64.7 64.1 64.3 –No price
17 Muse Wonder Meta 63.4 62.9 62.4 63.8 62.8 63.2 $8.00
23 Muse Spark 1.3 Meta 62.6 61.3 60.1 63.2 60.5 65.0 $0.13
24 Muse Ember New Meta 62.0 –No results 62.0 61.7 –No results 62.7 $0.20
46 Muse Spark Open Meta Open 59.1 58.4 57.0 58.8 59.6 58.9 $2.00
51 Muse Spark 1.2 Meta 59.0 57.6 57.5 60.1 57.4 59.4 $2.00
53 Muse Spark 1.1 Meta 58.7 58.3 57.4 60.2 56.8 58.8 $2.00
61 Muse Spark Meta 57.9 55.1 –No results 58.8 55.8 59.5 –No price
180 Llama 4 Maverick Meta Open 40.0 31.9 38.0 41.4 38.5 39.3 –No price
195 Llama 3.1-405B Meta Open 37.6 –No results –No results 39.2 35.6 –No results –No price
199 Llama 4 Scout Meta Open 36.9 25.9 33.7 37.7 35.8 –No results –No price
205 Llama-3.3-70B-Instruct Meta Open 36.2 31.8 36.4 38.1 33.7 –No results $0.72
218 Llama-3.1-70B-Instruct Meta Open 34.1 –No results 44.3 35.3 32.6 –No results $0.72
219 Llama-3.2-90B-Vision-Instruct Meta Open 33.5 –No results 44.0 34.2 32.6 –No results $0.000
221 Llama 3-70B Meta Open 32.9 –No results –No results 34.6 30.7 –No results –No price
227 Llama-3.1-8B-Instruct Meta Open 31.7 12.9 32.6 33.3 29.6 –No results $0.058
236 Llama 3-8B Meta Open 26.4 –No results –No results 27.5 25.0 –No results –No price
239 Llama 2-70B Meta Open 24.8 –No results –No results 27.6 21.3 –No results –No price