Modelpeers
GPT-6 Astra characterGPT-6.1 Sol character

GPT-6.1 Sol and GPT-6 Astra

2 models from OpenAI

Benchmark

Epoch: GPT-6.1 Sol matches GPT-6 Astra on FrontierMath tiers 1-3

Epoch's data records gpt-6.1-sol at max effort scoring 0.937 on FrontierMath tiers 1-3 (the same as GPT-6 Astra at max), 1.0 on FrontierMath tier 4 v2 and 0.954 on GPQA Diamond, from runs started September 29, 2026.

Source

"gpt-6.1-sol_max,0.9368421052631579"

Epoch AI benchmark data download (frontiermath_tiers_1_3_v2.csv)

Published

Open the sourceepoch.ai

Modelpeers tracks changes to AI agents and models, each from its source. Follow GPT-6.1 Sol to get a weekly email when it changes.