OpenAI

GPT-6 Sol

Sep 22, 2026ReasoningClosed weights

Compare

Intelligence

39.8

#65 of 744Rank 65 of 744 measured models

Output speed

114 t/s

#145 of 403Rank 145 of 403 measured models

Price/1M

$4

#532 of 659Rank 532 of 659 measured models

Context window

1.1M

#21 of 1199Rank 21 of 1199 measured models

Cost per task

$0.247

#78 of 193Rank 78 of 193 measured models

GPT-6 Sol (Medium) scores 39.8 on the Artificial Analysis Intelligence Index, ranking 65th of 744 measured models. The closest models on this index are Qwen3.8 2.4T A95B (39.9), Qwen3.8-Flash-Next (39.8), and Muse Spark 1.2 (Xhigh) (39.6). At $4 per million tokens (3:1 input/output blended price), it is more expensive than Qwen3.8 2.4T A95B ($3), Qwen3.8-Flash-Next ($0.23), and Muse Spark 1.2 (Xhigh) ($2). With an output speed of 114 t/s, it is faster than Qwen3.8 2.4T A95B (39.5 t/s) and Qwen3.8-Flash-Next (51.8 t/s), slower than Muse Spark 1.2 (Xhigh) (322 t/s).