Leaderboard
Agentic leaderboard
How well a model plans multi-step work, calls tools, and carries a task to completion without a human steering every turn. A value the source did not publish stays unavailable rather than becoming a zero.
Agentic leaderboard
229 source-backed models, ranked by agentic score. Blended cost is the 75% input / 25% output mix used everywhere else on the site.
| Rank | Model | Agentic | Overall | Blended $/1M |
|---|---|---|---|---|
| 1 | 93.6 | 80.46 | $8.00 | |
| 2 | 91 | 74.43 | $6.00 | |
| 3 | 89.1 | 81.41 | $20.00 | |
| 4 | 87.9 | 71.13 | $4.50 | |
| 5 | 87.1 | 82.81 | $20.00 | |
| 6 | 85.6 | 81.87 | $10.00 | |
| 7 | 83.6 | 73.17 | Unavailable | |
| 8 | 83.6 | 69.74 | $3.00 | |
| 9 | 83.6 | 66.93 | Unavailable | |
| 10 | 82.4 | 69.68 | $4.00 | |
| 11 | 82.4 | 64.29 | Unavailable | |
| 12 | 81.7 | 67.99 | $3.00 | |
| 13 | 81.4 | 70.28 | $2.00 | |
| 14 | 81.2 | 64.77 | $0.45 | |
| 15 | 81 | 66.06 | Unavailable | |
| 16 | 80.6 | 61.9 | $67.50 | |
| 17 | 80.2 | 68.42 | $3.00 | |
| 18 | 79.3 | 60.49 | $67.50 | |
| 19 | 78.4 | 66.68 | $2.15 | |
| 20 | 77.2 | 71.86 | $11.25 | |
| 21 | 76.8 | 42.56 | $3.00 | |
| 22 | 76.6 | 72.17 | $10.00 | |
| 23 | 75.9 | 70.18 | Unavailable | |
| 24 | 75.3 | 68.02 | $3.38 | |
| 25 | OAOrnith-1.5-397BOrnith AI · Open WeightSelf-hosted | 74.9 | 65.32 | Unavailable |
| 26 | 74.5 | 75.89 | $1.50 | |
| 27 | 72 | 70.88 | $5.63 | |
| 28 | 72 | 70.14 | $4.50 | |
| 29 | 71 | 65.6 | $1.71 | |
| 30 | DSdots3-note PreviewDots Studio · Open WeightSelf-hosted | 69.6 | 64.14 | Unavailable |
| 31 | 67.3 | 63.69 | $0.54 | |
| 32 | 66.5 | 59.73 | $1.56 | |
| 33 | 65.7 | 68.52 | $1.50 | |
| 34 | 64.7 | 69.31 | $10.00 | |
| 35 | 63.8 | 66.87 | Unavailable | |
| 36 | 63.5 | 69.21 | $10.00 | |
| 37 | 62.8 | 64.03 | $4.81 | |
| 38 | 60.8 | 84.74 | $20.00 | |
| 39 | 60.8 | 65.5 | $1.71 | |
| 40 | 60.3 | 62.61 | Unavailable | |
| 41 | 58.2 | 61.25 | $0.52 | |
| 42 | 58.1 | 61.6 | Unavailable | |
| 43 | TMInklingThinking Machines Lab · Open Weight | 57.6 | 60.38 | $2.57 |
| 44 | TMInkling-SmallThinking Machines Lab · Open Weight | 56.7 | 58.78 | $0.79 |
| 45 | 56.6 | 57.78 | Unavailable | |
| 46 | 56 | 63.94 | Unavailable | |
| 47 | 55.5 | 61.05 | $1.69 | |
| 48 | 52.5 | 60.36 | Unavailable | |
| 49 | 51.8 | 58.78 | $0.85 | |
| 50 | 51.6 | 46.83 | Unavailable | |
| 51 | 51.2 | 45.08 | $0.64 | |
| 52 | 50.5 | 62.86 | $6.00 | |
| 53 | 50.4 | 49.78 | $0.44 | |
| 54 | 47.3 | 58.42 | $10.00 | |
| 55 | 47.2 | 47.73 | Unavailable | |
| 56 | 46.9 | 63.26 | $2.15 | |
| 57 | 46.8 | 67.51 | Unavailable | |
| 58 | OAOrnith-1.5-35B-A3BOrnith AI · Open WeightSelf-hosted | 44.2 | 36.86 | Unavailable |
| 59 | 43.9 | 55.01 | $0.52 | |
| 60 | 42.8 | 61.47 | $1.55 | |
| 61 | 41 | 56.98 | Unavailable | |
| 62 | 40.2 | 55.71 | $0.29 | |
| 63 | 38.7 | 70.6 | $10.00 | |
| 64 | 36 | 43.85 | Unavailable | |
| 65 | 33.7 | 54.01 | $6.00 | |
| 66 | 30.9 | 55.09 | $1.35 | |
| 67 | 29.7 | 67.27 | $3.00 | |
| 68 | 28.1 | 50.84 | Unavailable | |
| 69 | 28 | 57.39 | $1.20 | |
| 70 | 28 | 54.02 | $1.20 | |
| 71 | 27.8 | 3.81 | Unavailable | |
| 72 | 27.3 | 40.5 | Unavailable | |
| 73 | 24.9 | 50.67 | Unavailable | |
| 74 | 23.1 | 64.86 | $4.81 | |
| 75 | 20.9 | 1.47 | Unavailable | |
| 76 | 18.5 | 59.42 | $0.46 | |
| 77 | 15.5 | 55.14 | Unavailable | |
| 78 | 13.7 | 53.47 | Unavailable | |
| 79 | 10.8 | 57.76 | Unavailable | |
| 80 | 10.8 | 20.46 | Unavailable | |
| 81 | Unavailable | 68.99 | $57.75 | |
| 82 | Unavailable | 66.36 | $4.50 | |
| 83 | Unavailable | 63.18 | $3.44 | |
| 84 | Unavailable | 62.51 | Unavailable | |
| 85 | Unavailable | 62.23 | Unavailable | |
| 86 | Unavailable | 61.94 | $1.13 | |
| 87 | Unavailable | 61.42 | $1.90 | |
| 88 | Unavailable | 60.89 | $1.25 | |
| 89 | Unavailable | 60.79 | $0.14 | |
| 90 | Unavailable | 59.32 | Unavailable | |
| 91 | Unavailable | 57.99 | Unavailable | |
| 92 | Unavailable | 57.81 | $1.55 | |
| 93 | Unavailable | 57.54 | $1.35 | |
| 94 | Unavailable | 57.53 | Unavailable | |
| 95 | Unavailable | 57.41 | $1.90 | |
| 96 | Unavailable | 57.31 | $3.44 | |
| 97 | Unavailable | 57.05 | $2.63 | |
| 98 | Unavailable | 56.95 | $4.81 | |
| 99 | Unavailable | 56.81 | $0.32 | |
| 100 | Unavailable | 56.7 | $3.44 | |
| 101 | Unavailable | 56.32 | $0.56 | |
| 102 | Unavailable | 56.19 | $0.96 | |
| 103 | Unavailable | 56.19 | $0.18 | |
| 104 | Unavailable | 56.08 | Unavailable | |
| 105 | Unavailable | 55.64 | $1.00 | |
| 106 | Unavailable | 55 | Unavailable | |
| 107 | Unavailable | 54.99 | Unavailable | |
| 108 | Unavailable | 54.82 | Unavailable | |
| 109 | Unavailable | 54.76 | $0.52 | |
| 110 | Unavailable | 54.11 | Unavailable | |
| 111 | Unavailable | 54.04 | $0.44 | |
| 112 | Unavailable | 53.95 | $4.81 | |
| 113 | Unavailable | 53.4 | Unavailable | |
| 114 | Unavailable | 53.05 | Unavailable | |
| 115 | Unavailable | 52.89 | $2.00 | |
| 116 | Unavailable | 52.65 | Unavailable | |
| 117 | Unavailable | 52.6 | $3.44 | |
| 118 | Unavailable | 52.4 | Unavailable | |
| 119 | Unavailable | 51.85 | Unavailable | |
| 120 | APApodex 1.1Apodex · Proprietary | Unavailable | 51.74 | Unavailable |
| 121 | Unavailable | 51.73 | Unavailable | |
| 122 | Unavailable | 51.24 | $0.85 | |
| 123 | Unavailable | 51.16 | Unavailable | |
| 124 | Unavailable | 51.09 | Unavailable | |
| 125 | PMTernary Bonsai 2 27BPrism ML · Open WeightSelf-hosted | Unavailable | 50.78 | $0.18 |
| 126 | Unavailable | 50.72 | Unavailable | |
| 127 | Unavailable | 50.55 | $0.96 | |
| 128 | Unavailable | 50.33 | $0.90 | |
| 129 | Unavailable | 49.68 | $0.15 | |
| 130 | Unavailable | 49.62 | Unavailable | |
| 131 | Unavailable | 49.46 | $0.055 | |
| 132 | Unavailable | 49.15 | $0.17 | |
| 133 | Unavailable | 48.83 | Unavailable | |
| 134 | Unavailable | 48.67 | Unavailable | |
| 135 | Unavailable | 48.48 | Unavailable | |
| 136 | Unavailable | 48.43 | Unavailable | |
| 137 | Unavailable | 48.28 | Unavailable | |
| 138 | Unavailable | 48.2 | $1.93 | |
| 139 | Unavailable | 48.16 | $3.44 | |
| 140 | Unavailable | 48.09 | Unavailable | |
| 141 | Unavailable | 48.09 | Unavailable | |
| 142 | Unavailable | 48.04 | Unavailable | |
| 143 | Unavailable | 47.84 | $35.00 | |
| 144 | Unavailable | 47.58 | $3.50 | |
| 145 | Unavailable | 47.56 | $0.20 | |
| 146 | Unavailable | 47.14 | $0.28 | |
| 147 | Unavailable | 46.98 | $0.35 | |
| 148 | ALAion-2.0Aion Labs · Proprietary | Unavailable | 46.89 | $1.00 |
| 149 | Unavailable | 46.72 | $1.93 | |
| 150 | Unavailable | 46.19 | $26.25 | |
| 151 | Unavailable | 46.13 | Unavailable | |
| 152 | Unavailable | 46.09 | $26.25 | |
| 153 | Unavailable | 45.82 | $0.26 | |
| 154 | Unavailable | 45.45 | $0.75 | |
| 155 | Unavailable | 45 | $0.69 | |
| 156 | Unavailable | 43.73 | $0.43 | |
| 157 | Unavailable | 43.43 | Unavailable | |
| 158 | Unavailable | 43.39 | Unavailable | |
| 159 | Unavailable | 43.29 | Unavailable | |
| 160 | Unavailable | 43.27 | $0.41 | |
| 161 | Unavailable | 43.1 | Unavailable | |
| 162 | Unavailable | 42.99 | Unavailable | |
| 163 | Unavailable | 42.91 | Unavailable | |
| 164 | Unavailable | 42.85 | $4.38 | |
| 165 | Unavailable | 42.85 | $0.26 | |
| 166 | Unavailable | 42.72 | Unavailable | |
| 167 | Unavailable | 42.17 | $0.38 | |
| 168 | Unavailable | 42.05 | $262.50 | |
| 169 | Unavailable | 41.87 | $30.00 | |
| 170 | Unavailable | 41.64 | $0.48 | |
| 171 | Unavailable | 41.29 | $3.50 | |
| 172 | Unavailable | 41.08 | $0.055 | |
| 173 | Unavailable | 40.89 | Unavailable | |
| 174 | Unavailable | 40.75 | $1.56 | |
| 175 | Unavailable | 40.59 | Unavailable | |
| 176 | Unavailable | 40.18 | Unavailable | |
| 177 | SASarvam 105BSarvam · Open WeightSelf-hosted | Unavailable | 40.12 | Unavailable |
| 178 | Unavailable | 39.9 | Unavailable | |
| 179 | Unavailable | 39.58 | Unavailable | |
| 180 | Unavailable | 39.28 | Unavailable | |
| 181 | Unavailable | 39.26 | $6.00 | |
| 182 | SASarvam 30BSarvam · Open WeightSelf-hosted | Unavailable | 38.93 | Unavailable |
| 183 | Unavailable | 38.81 | $4.38 | |
| 184 | Unavailable | 38.79 | $0.15 | |
| 185 | Unavailable | 38.64 | Unavailable | |
| 186 | Unavailable | 38.27 | Unavailable | |
| 187 | Unavailable | 38.27 | Unavailable | |
| 188 | Unavailable | 38.22 | Unavailable | |
| 189 | Unavailable | 38.21 | Unavailable | |
| 190 | Unavailable | 38.06 | Unavailable | |
| 191 | Unavailable | 38.02 | Unavailable | |
| 192 | Unavailable | 38.02 | Unavailable | |
| 193 | Unavailable | 37.94 | $0.10 | |
| 194 | Unavailable | 37.56 | Unavailable | |
| 195 | Unavailable | 37.52 | Unavailable | |
| 196 | Unavailable | 36.91 | $0.14 | |
| 197 | Unavailable | 36.7 | Unavailable | |
| 198 | Unavailable | 36.33 | Unavailable | |
| 199 | Unavailable | 35.73 | Unavailable | |
| 200 | Unavailable | 34.4 | $30.00 | |
| 201 | Unavailable | 34.02 | $0.53 | |
| 202 | Unavailable | 33.46 | $2.19 | |
| 203 | Unavailable | 33.36 | $0.70 | |
| 204 | Unavailable | 33.32 | $0.15 | |
| 205 | Unavailable | 33.3 | Unavailable | |
| 206 | Unavailable | 33.26 | $0.26 | |
| 207 | Unavailable | 33.09 | $0.0875 | |
| 208 | Unavailable | 32.54 | Unavailable | |
| 209 | Unavailable | 32.09 | $6.00 | |
| 210 | Unavailable | 31.4 | Unavailable | |
| 211 | Unavailable | 30.73 | Unavailable | |
| 212 | Unavailable | 30.64 | $0.80 | |
| 213 | Unavailable | 30.19 | $0.20 | |
| 214 | Unavailable | 27.21 | $0.18 | |
| 215 | Unavailable | 26.85 | Unavailable | |
| 216 | Unavailable | 24.4 | $15.00 | |
| 217 | Unavailable | 23.12 | $1.08 | |
| 218 | Unavailable | 22.73 | $0.30 | |
| 219 | Unavailable | 21.38 | Unavailable | |
| 220 | Unavailable | 19.04 | Unavailable | |
| 221 | Unavailable | 18.48 | Unavailable | |
| 222 | Unavailable | 17.96 | $0.50 | |
| 223 | Unavailable | 17.78 | $0.15 | |
| 224 | Unavailable | 16.65 | Unavailable | |
| 225 | Unavailable | 16.32 | Unavailable | |
| 226 | Unavailable | 15.97 | Unavailable | |
| 227 | Unavailable | 15.96 | $0.10 | |
| 228 | Unavailable | 15.9 | Unavailable | |
| 229 | Unavailable | 8.66 | Unavailable |
Evidence key: ObservedUnavailable
68 of these rows are marked self-hosted by the source: open-weight models with no first-party hosted token rate. 11 of them show a hosted rate matched from another provider; the rest report an unavailable price rather than zero.