BGE Base En V1.5π¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 86.7From 152 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.01 | β | 512 | βNot enough data yet |
Mistral (7B) Instruct v0.3π«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 85.5From 276 benchmarks. Plenty of data behind it. | βNot enough data yet | $0.11 | $0.11 | 127K | 47.1Poor value (47.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
| βNot enough data yet | βNot enough data yet | $0.19 | $0.19 | 256K | βNot enough data yet |
llava-v1.6-mistral-7b-hfπ«π·Maker headquartered in FR, according to the company's own website. The citation is on the model page. | βNot enough data yet | βNot enough data yet | $0.29 | $0.29 | 32K | βNot enough data yet |
clef flash
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βDoesnβt apply to this model | βDoesnβt apply to this model | β | βDoesnβt apply to this model | 16K | βDoesnβt apply to this model |
Nemotron Nano 3 30BπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. nemotron3-nano-30bnemotron3-nano-30b | βNot enough data yet | βNot enough data yet | β | β | 262K | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
Qwen3Guard Gen 0.6Bπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | 33K | βNot enough data yet |
Qwen3Guard Gen 8Bπ¨π³Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | 33K | βNot enough data yet |
| βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | βNot enough data yet |
Whisper Large V3πΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | 55.6Good value (55.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |
Whisper Large V3 TurboπΊπΈMaker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | βNot enough data yet | βNot enough data yet | β | β | βNot published by the provider | 61.1Good value (61.1). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. |