{"task":"Multi-task Language Understanding","dataset":"BBH-alg","metric_names":["Average (%)"],"rows":[{"id":22687,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"code-davinci-002 175B (CoT)","metrics":{"Average (%)":"73.9"},"paper_url":"https://arxiv.org/abs/2107.03374v2","paper_title":"Evaluating Large Language Models Trained on Code","paper_date":"2021-07-07","code_links":[{"title":"THUDM/CodeGeeX","url":"https://github.com/THUDM/CodeGeeX"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"openai/human-eval","url":"https://github.com/openai/human-eval"},{"title":"vhellendoorn/code-lms","url":"https://github.com/vhellendoorn/code-lms"},{"title":"glouppe/info8010-deep-learning","url":"https://github.com/glouppe/info8010-deep-learning"},{"title":"microsoft/PythonProgrammingPuzzles","url":"https://github.com/microsoft/PythonProgrammingPuzzles"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"codefuse-ai/codefuse-evaluation","url":"https://github.com/codefuse-ai/codefuse-evaluation"},{"title":"my-other-github-account/llm-humaneval-benchmarks","url":"https://github.com/my-other-github-account/llm-humaneval-benchmarks"},{"title":"superli3/codenavi","url":"https://github.com/superli3/codenavi"},{"title":"superli3/CYRMPR","url":"https://github.com/superli3/CYRMPR"},{"title":"2796gaurav/human-eval","url":"https://github.com/2796gaurav/human-eval"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22688,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned, CoT + SC)","metrics":{"Average (%)":"66.5"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22689,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B (CoT + self-consistency)","metrics":{"Average (%)":"62.2"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22690,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned, CoT)","metrics":{"Average (%)":"61.3"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22691,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B (CoT)","metrics":{"Average (%)":"57.6"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22692,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned)","metrics":{"Average (%)":"48.2"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":22693,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B","metrics":{"Average (%)":"38.3"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112587,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"code-davinci-002 175B (CoT)","metrics":{"Average (%)":"73.9"},"paper_url":"https://arxiv.org/abs/2107.03374v2","paper_title":"Evaluating Large Language Models Trained on Code","paper_date":"2021-07-07","code_links":[{"title":"THUDM/CodeGeeX","url":"https://github.com/THUDM/CodeGeeX"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"openai/human-eval","url":"https://github.com/openai/human-eval"},{"title":"vhellendoorn/code-lms","url":"https://github.com/vhellendoorn/code-lms"},{"title":"glouppe/info8010-deep-learning","url":"https://github.com/glouppe/info8010-deep-learning"},{"title":"microsoft/PythonProgrammingPuzzles","url":"https://github.com/microsoft/PythonProgrammingPuzzles"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"codefuse-ai/codefuse-evaluation","url":"https://github.com/codefuse-ai/codefuse-evaluation"},{"title":"my-other-github-account/llm-humaneval-benchmarks","url":"https://github.com/my-other-github-account/llm-humaneval-benchmarks"},{"title":"superli3/codenavi","url":"https://github.com/superli3/codenavi"},{"title":"superli3/CYRMPR","url":"https://github.com/superli3/CYRMPR"},{"title":"2796gaurav/human-eval","url":"https://github.com/2796gaurav/human-eval"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112588,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned, CoT + SC)","metrics":{"Average (%)":"66.5"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112589,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B (CoT + self-consistency)","metrics":{"Average (%)":"62.2"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112590,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned, CoT)","metrics":{"Average (%)":"61.3"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112591,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B (CoT)","metrics":{"Average (%)":"57.6"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112592,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"Flan-PaLM 540B (3-shot, fine-tuned)","metrics":{"Average (%)":"48.2"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":112593,"task":"Multi-task Language Understanding","parent_task":"Multi-Task Learning","dataset":"BBH-alg","model_name":"PaLM 540B","metrics":{"Average (%)":"38.3"},"paper_url":"https://arxiv.org/abs/2210.11416v5","paper_title":"Scaling Instruction-Finetuned Language Models","paper_date":"2022-10-20","code_links":[{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"declare-lab/flan-alpaca","url":"https://github.com/declare-lab/flan-alpaca"},{"title":"formulamonks/llm-benchmarker-suite","url":"https://github.com/formulamonks/llm-benchmarker-suite"},{"title":"theoremone/llm-benchmarker-suite","url":"https://github.com/theoremone/llm-benchmarker-suite"},{"title":"zchuz/timebench","url":"https://github.com/zchuz/timebench"},{"title":"coastalcph/zeroshot_lexglue","url":"https://github.com/coastalcph/zeroshot_lexglue"},{"title":"joelniklaus/lawinstruct","url":"https://github.com/joelniklaus/lawinstruct"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"kapllan/zeroshot_lexglue","url":"https://github.com/kapllan/zeroshot_lexglue"}],"metrics_order":"[\"Average (%)\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]}]}