Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Custom ranking
Decide how much each capability matters. Each weight is multiplied by that factor's score and the products are summed; a factor the source has no value for contributes nothing, and every row says how many of your weighted factors it was measured on.
Set how much each capability matters. Weights are relative; a weight of zero removes an axis entirely.
A model with no runtime measurement cannot satisfy a threshold, so an active threshold excludes it rather than assuming it passes.
Catalog score against the 75% input / 25% output blended token price, limited to the models passing your filters. Frontier models are spaced evenly along the cost axis.
109 of these rows are marked self-hosted by the source: open-weight models with no first-party hosted token rate. 12 of them show a hosted rate matched from another provider; the rest report an unavailable price rather than zero.
323 ranked by weighted total · 146 with no value on any weighted factor
Evidence key: Derived
| Compare | Rank | Model | Weighted total | Factors | Blended $/1M | TTFT | Throughput |
|---|---|---|---|---|---|---|---|
| 1 | 1720.8 | 7/7 | $8.00 | 100.66 s | 94 tok/s | ||
| 2 | 1693.5 | 7/7 | Unavailable | 52.16 s | 41 tok/s | ||
| 3 | 1687.2 | 7/7 | $20.00 | 100.13 s | 68 tok/s | ||
| 4 | 1611.6 | 7/7 | $4.50 | Unavailable | 64 tok/s | ||
| 5 | 1598.1 | 7/7 | $11.25 | 37.05 s | 98 tok/s | ||
| 6 | 1579.5 | 7/7 | $10.00 | 35.96 s | 65 tok/s | ||
| 7 | 1552.2 | 6/7 | $20.00 | 204.16 s | 42 tok/s | ||
| 8 | 1537.2 | 6/7 | $10.00 | 59.73 s | 62 tok/s | ||
| 9 | 1534.5 | 7/7 | $4.50 | 15.39 s | 115 tok/s | ||
| 10 | 1523.1 | 7/7 | $5.63 | 157.51 s | 89 tok/s | ||
| 11 | 1519.5 | 6/7 | $4.00 | Unavailable | 38 tok/s | ||
| 12 | 1500.0 | 6/7 | $20.00 | 128.91 s | 66 tok/s | ||
| 13 | 1497.6 | 6/7 | $8.00 | 359.2 s | 117 tok/s | ||
| 14 | 1496.7 | 7/7 | $3.38 | 12.96 s | 188 tok/s | ||
| 15 | 1492.5 | 7/7 | Unavailable | 46.43 s | 56 tok/s | ||
| 16 | 1468.8 | 6/7 | $4.00 | 286.89 s | 147 tok/s | ||
| 17 | 1436.7 | 7/7 | $10.00 | 18.77 s | 58 tok/s | ||
| 18 | 1427.4 | 7/7 | $1.56 | 24.18 s | 105 tok/s | ||
| 19 | TMInkling 2 SmallThinking Machines Lab · Proprietary | 1424.4 | 6/7 | $0.48 | Unavailable | 145.5 tok/s | |
| 20 | 1421.4 | 6/7 | $4.00 | Unavailable | 50 tok/s | ||
| 21 | 1413.9 | 7/7 | Unavailable | 100.68 s | 56 tok/s | ||
| 22 | TMInklingThinking Machines Lab · Open Weight | 1412.7 | 7/7 | $2.57 | 17.31 s | 100 tok/s | |
| 23 | TMInkling-SmallThinking Machines Lab · Open Weight | 1397.7 | 7/7 | $0.79 | Unavailable | 98 tok/s | |
| 24 | 1397.1 | 6/7 | $4.81 | 38.22 s | 89 tok/s | ||
| 25 | 1385.7 | 6/7 | Unavailable | 14.47 s | 197 tok/s |
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Prices shown are the 75% input / 25% output blend of the source input and output rates — for example GPT-5.6 Sol at $4.00 in and $20.00 out.