| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_t5-11b,stop=hash | generation |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_yalm | generation |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-instruct-30 | generation |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-base | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-extended | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-supreme | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande-v2-beta | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-jumbo | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-large | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-grande | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-jumbo | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-large | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=anthropic_stanford-online-all-v4-s3 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_command-medium-beta | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_command-xlarge-beta | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_large-20220720 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_medium-20220720 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_medium-20221108 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_small-20220720 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_xlarge-20220609 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_xlarge-20221108 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=microsoft_TNLGv2_530B | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=microsoft_TNLGv2_7B | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_ada | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_babbage | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_code-cushman-001 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_code-davinci-002 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_curie | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_davinci | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_gpt-3.5-turbo-0301 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-ada-001 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-babbage-001 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-curie-001 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-davinci-002 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-davinci-003 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_bloom | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_glm,stop=hash | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_gpt-j-6b | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_gpt-neox-20b | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_opt-175b | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_opt-66b | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_redpajama-incite-base-3b-v1 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_t0pp,stop=hash | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_t5-11b,stop=hash | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_yalm | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=writer_palmyra-instruct-30 | generation |
| math:subject=algebra,level=1,use_official_examples=True,use_chain_of_thought=False,model=writer_palmyra-x | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-base | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-extended | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-supreme | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-grande | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-grande-v2-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-jumbo | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-large | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-grande | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-jumbo | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-large | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=anthropic_stanford-online-all-v4-s3 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_command-medium-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_command-xlarge-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_large-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_medium-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_medium-20221108 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_small-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_xlarge-20220609 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_xlarge-20221108 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_TNLGv2_530B | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_TNLGv2_7B | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_ada | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_babbage | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_code-cushman-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_code-davinci-002 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_curie | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_davinci | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-3.5-turbo-0301 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-ada-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-babbage-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-curie-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-davinci-002 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-davinci-003 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_bloom | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_glm,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_gpt-j-6b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_gpt-neox-20b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_opt-175b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_opt-66b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_redpajama-incite-base-3b-v1 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_t0pp,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_t5-11b,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_yalm | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-instruct-30 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-base | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-extended | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-supreme | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande-v2-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-jumbo | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-large | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-grande | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-jumbo | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-large | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=anthropic_stanford-online-all-v4-s3 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_command-medium-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_command-xlarge-beta | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_large-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_medium-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_medium-20221108 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_small-20220720 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_xlarge-20220609 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=cohere_xlarge-20221108 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=microsoft_TNLGv2_530B | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=microsoft_TNLGv2_7B | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_ada | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_babbage | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_code-cushman-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_code-davinci-002 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_curie | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_davinci | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_gpt-3.5-turbo-0301 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-ada-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-babbage-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-curie-001 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-davinci-002 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=openai_text-davinci-003 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_bloom | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_glm,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_gpt-j-6b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_gpt-neox-20b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_opt-175b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_opt-66b | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_redpajama-incite-base-3b-v1 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_t0pp,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_t5-11b,stop=hash | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=together_yalm | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=writer_palmyra-instruct-30 | generation |
| math:subject=counting_and_probability,level=1,use_official_examples=True,use_chain_of_thought=False,model=writer_palmyra-x | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-base | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-extended | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=AlephAlpha_luminous-supreme | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-grande | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-grande-v2-beta | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-jumbo | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j1-large | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-grande | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-jumbo | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_j2-large | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=anthropic_stanford-online-all-v4-s3 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_command-medium-beta | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_command-xlarge-beta | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_large-20220720 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_medium-20220720 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_medium-20221108 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_small-20220720 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_xlarge-20220609 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=cohere_xlarge-20221108 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_TNLGv2_530B | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_TNLGv2_7B | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_ada | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_babbage | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_code-cushman-001 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_code-davinci-002 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_curie | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_davinci | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-3.5-turbo-0301 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-ada-001 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-babbage-001 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-curie-001 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-davinci-002 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_text-davinci-003 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_bloom | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_glm,stop=hash | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_gpt-j-6b | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_gpt-neox-20b | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_opt-175b | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_opt-66b | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_redpajama-incite-base-3b-v1 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_t0pp,stop=hash | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_t5-11b,stop=hash | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_ul2,stop=hash,global_prefix=nlg | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=together_yalm | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-instruct-30 | generation |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=writer_palmyra-x | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-base | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-extended | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=AlephAlpha_luminous-supreme | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-grande-v2-beta | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-jumbo | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j1-large | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-grande | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-jumbo | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=ai21_j2-large | generation |
| math:subject=geometry,level=1,use_official_examples=True,use_chain_of_thought=False,model=anthropic_stanford-online-all-v4-s3 | generation |