Timeline of Nous Research

Hermes 3 70B Instruct scores 40.1% on GPQA

Hermes 3 70B Instruct scores 6 on Artificial Analysis Intelligence Index

hermes-4-llama-3-1-70b scores 0% on Terminal-Bench

hermes-4-llama-3-1-70b scores 21.64% on τ²-bench

hermes-4-llama-3-1-70b scores 28.98% on IFBench

hermes-4-llama-3-1-70b scores 3.57% on Humanity's Last Exam

hermes-4-llama-3-1-70b scores 49.09% on GPQA

hermes-4-llama-3-1-70b scores 6.66 on Artificial Analysis Intelligence Index

Hermes-4-70B scores 4.55% on Terminal-Bench

Hermes-4-70B scores 22.51% on τ²-bench

Hermes-4-70B scores 31.29% on IFBench

Hermes-4-70B scores 8.76% on Humanity's Last Exam

Hermes-4-70B scores 69.9% on GPQA

Hermes-4-70B scores 7.91 on Artificial Analysis Intelligence Index

Hermes 4 405B scores 11.36% on Terminal-Bench

Hermes 4 405B scores 22.22% on τ²-bench

Hermes 4 405B scores 32.72% on IFBench

Hermes 4 405B scores 10.89% on Humanity's Last Exam

Hermes 4 405B scores 72.73% on GPQA

Hermes 4 405B scores 7.49 on Artificial Analysis Intelligence Index

deephermes-3-mistral-24b-preview scores 3.76% on Humanity's Last Exam

deephermes-3-mistral-24b-preview scores 38.18% on GPQA

deephermes-3-mistral-24b-preview scores 6.07 on Artificial Analysis Intelligence Index

deephermes-3-llama-3-1-8b-preview scores 4.26% on Humanity's Last Exam

deephermes-3-llama-3-1-8b-preview scores 26.97% on GPQA

deephermes-3-llama-3-1-8b-preview scores 5.08 on Artificial Analysis Intelligence Index

hermes-4-llama-3-1-405b scores 9.85% on Terminal-Bench

hermes-4-llama-3-1-405b scores 26.61% on τ²-bench

hermes-4-llama-3-1-405b scores 34.76% on IFBench

hermes-4-llama-3-1-405b scores 4.22% on Humanity's Last Exam

hermes-4-llama-3-1-405b scores 53.64% on GPQA

hermes-4-llama-3-1-405b scores 7.41 on Artificial Analysis Intelligence Index