Spaces:
Running
Running
model,link,assin2_sts,assin2_rte,faquad_nli,hatebr_offensive | |
sabia-2-small,https://www.maritaca.ai/,0.7053302344881672,0.9121728362223306,0.7575848453041435,0.753800795680591 | |
sabia-2-medium,https://www.maritaca.ai/,0.7804108376537757,0.923459363368553,0.7657657657657658,0.8349989882997386 | |
gpt-3.5-turbo-0125,https://www.openai.com/,0.7378460201077941,0.8823038414050672,0.746353108609074,0.8056205941193919 | |
claude-3-haiku-20240307,https://www.claude.ai/,0.7892124744168747,0.9184462138121732,0.6340996599941455,0.8023698759439051 | |
gemini-1.0-pro,https://ai.google.dev/,0.7058831239763663,0.8945993304651698,0.7070913567220611,0.8086330094493972 | |
gemini-1.5-pro-preview-0409,https://cloud.google.com/vertex-ai,0.8159702278408203,0.9328989988467518,0.7290756302521009,0.8697698647467024 | |
deepseek-v2-chat,https://www.deepseek.com/,0.8533174657651231,0.9440170304568147,0.7995469048381548,0.8842986491071644 | |
gemini-1.5-flash-preview-0514,https://cloud.google.com/vertex-ai,0.841655158151231,0.9362097477374545,0.8092185592185592,0.9099110141445836 | |
gemini-1.5-flash-001,https://cloud.google.com/vertex-ai,0.838806085610371,0.9366169973822607,0.7963910785668922,0.9092078461170015 | |
gpt-4o-mini-2024-07-18,https://www.openai.com/,0.7259038954527597,0.942809846745341,0.819807735300693,0.8682357029532165 | |
nemotron-4-340b-instruct,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct,0.7857731021403329,0.9489354458928496,0.8194444444444444,0.8641580001234928 | |
llama_405b_instruct,https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct,0.7888441732870783,0.9476445477916471,0.825063276593557,0.9073940659389119 | |
sabia-3,https://www.maritaca.ai/,0.8253863689009022,0.9477034821619312,0.8243848812618203,0.8278737774590023 | |
llama3_3_70b,https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct,0.7275578599896508,0.9407071010860484,0.8787563033858187,0.9024358249091997 | |
llama3_2_90b,https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct,0.7368518566379951,0.9216548775103446,0.8632015306122449,0.8965270877302478 | |
gemini-1.5-flash-002,https://cloud.google.com/vertex-ai,0.8380176734291938,0.941176117215237,0.8360786822325283,0.9046145161133335 | |
gemini-1.5-flash-8b-001,https://aistudio.google.com,0.7638946799836569,0.9329452628161146,0.7937022965448601,0.850497640901663 | |
gemini-2.0-flash-001,https://cloud.google.com/vertex-ai,0.8440142633742483,0.9305165510724053,0.7533651260745065,0.8890432813545366 | |
gemini-2.0-flash-lite-001,https://cloud.google.com/vertex-ai,0.8492479991621328,0.9216548775103446,0.7652777777777777,0.8522499647780968 | |
gemini-2.5-pro-exp-03-25,https://aistudio.google.com,0.837785744915033,0.9415510158830285,0.8738735797309651,0.9248478168290788 | |
deepSeek-v3-0324,https://huggingface.co/deepseek-ai/DeepSeek-V3-0324,0.8145997097875548,0.9421860387625551,0.796751127001399,0.9060129756724185 | |
qwen2-5-vl-72b-instruct,https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct,0.7595538567467497,0.9472975104201871,0.8447190882122586,0.8810695094657859 | |
qwen2-5-72b-instruct,https://huggingface.co/Qwen/Qwen2.5-72B-Instruct,0.8230708844558656,0.9509720145268106,0.8194444444444444,0.8810033427242816 | |
qwen2-5-vl-32b-instruct,https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct,0.7780549055529008,0.9472975104201871,0.8447190882122586,0.8810695094657859 | |
qwen-turbo-2024-11-01,https://www.alibabacloud.com/en/product/modelstudio,0.7640477700456898,0.9260451969385788,0.8128063725490196,0.8567933277676292 | |
gpt-4o-2024-08-06,https://www.openai.com/,0.8078677969518289,0.9407235712144604,0.8654396266184885,0.9320137873994456 | |
claude-3-7-sonnet-20250219,https://www.anthropic.com/,0.8087979933117393,0.9472965253044003,0.8097848807348216,0.9125114739050616 | |
llama-4-scout-16e,https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct,0.7741640227983941,0.9312877465954967,0.8567037452287072,0.8813700069483281 | |
llama-4-maverick-128e,https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct,0.7333246903202654,0.9329419027588105,0.7823695413019562,0.9047550357833591 | |
gemma-3-27b-it,https://huggingface.co/google/gemma-3-27b-it,0.8147646517017526,0.9411147367212748,0.8143210816987241,0.8729414870796344 | |