| 1 | Phi-3.5-MoE-instruct | microsoft/Phi-3.5-MoE-instruct | microsoft | 67.1 | medium | MEGA TyDi QA |
| 2 | llama-3-tulu-2-8b | meta-llama/Meta-Llama-3-8B | allenai | 66.8 | low | GSM8k 8-shot cot | BBH 3-shot cot |
| 3 | llama-3-tulu-2-70b | meta-llama/Meta-Llama-3-70B | allenai | 66.8 | low | GSM8k 8-shot cot | BBH 3-shot cot |
| 4 | Phi-3.5-mini-instruct | microsoft/Phi-3.5-mini-instruct | microsoft | 62.2 | medium | MEGA TyDi QA |
| 5 | Phi-3.5-mini-instruct-bnb-4bit | microsoft/Phi-3.5-mini-instruct | unsloth | 62.2 | medium | MEGA TyDi QA |
| 6 | Phi-3.5-mini-instruct | microsoft/Phi-3.5-mini-instruct | unsloth | 62.2 | medium | MEGA TyDi QA |
| 7 | open-instruct-human-mix-65B-GGUF | allenai/open-instruct-human-mix-65b | TheBloke | 58.5 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 8 | open-instruct-human-mix-65b | allenai/open-instruct-human-mix-65b | allenai | 58.5 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 9 | tulu-30B-GGUF | allenai/tulu-30b | TheBloke | 58.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 10 | tulu-30B-fp16 | — | TheBloke | 58.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 11 | tulu-30b | allenai/tulu-30b | allenai | 58.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 12 | tulu-30B-GPTQ | allenai/tulu-30b | TheBloke | 58.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 13 | open-instruct-cot-13b | allenai/open-instruct-cot-13b | allenai | 52.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 14 | tulu-65b | allenai/tulu-65b | allenai | 51.8 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 15 | open-instruct-sni-7b | allenai/open-instruct-sni-7b | allenai | 47.9 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 16 | tulu-13B-GGUF | allenai/tulu-13b | TheBloke | 46.1 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 17 | tulu-13B-fp16 | — | TheBloke | 46.1 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 18 | tulu-7B-GGUF | allenai/tulu-7b | TheBloke | 45.7 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 19 | tulu-7b | allenai/tulu-7b | allenai | 45.7 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 20 | tulu-7B-fp16 | — | TheBloke | 45.7 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 21 | open-instruct-flan-v2-7b | allenai/open-instruct-flan-v2-7b | allenai | 45.0 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 22 | open-instruct-cot-7b | allenai/open-instruct-cot-7b | allenai | 44.4 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 23 | open-instruct-dolly-7b | allenai/open-instruct-dolly-7b | allenai | 43.6 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 24 | open-instruct-human-mix-7b | allenai/open-instruct-human-mix-7b | allenai | 42.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 25 | open-instruct-code-alpaca-7b | allenai/open-instruct-code-alpaca-7b | allenai | 36.7 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 26 | open-instruct-unnatural-instructions-7b | allenai/open-instruct-unnatural-instructions-7b | allenai | 36.3 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 27 | open-instruct-self-instruct-7b | allenai/open-instruct-self-instruct-7b | allenai | 35.4 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 28 | open-instruct-pythia-6.9b-tulu | allenai/open-instruct-pythia-6.9b-tulu | allenai | 33.4 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 29 | open-instruct-stanford-alpaca-7b | allenai/open-instruct-stanford-alpaca-7b | allenai | 31.2 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 30 | open-instruct-baize-7b | allenai/open-instruct-baize-7b | allenai | 29.8 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 31 | open-instruct-oasst1-7b | allenai/open-instruct-oasst1-7b | allenai | 26.8 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 32 | open-instruct-sharegpt-7b | allenai/open-instruct-sharegpt-7b | allenai | 25.5 | low | GSM CoT | BBH CoT | TydiQA Closed-book |
| 33 | open-instruct-gpt4-alpaca-7b | allenai/open-instruct-gpt4-alpaca-7b | allenai | 23.6 | low | GSM CoT | BBH CoT | TydiQA Closed-book |