Compare / GPT-5.4 vs GPT-6.1 Sol

GPT-5.4 vs GPT-6.1 Sol

5 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

GPT-5.4: OpenAI · profile
GPT-6.1 Sol: OpenAI · profile
Results compared: 5
Shared sources: 3

Benchmark	Metric	GPT-5.4	GPT-6.1 Sol
APEX-Agentsreported	Tasks passed% of tasks	52.4%	60.0%
Artificial Analysisreported	Artificial Analysis Intelligence Indexindex score	39.0	51.8
Artificial Analysisreported	Humanity's Last Exam% of questions	43.7%	52.9%
Artificial Analysisreported	Long-context reasoning (AA-LCR)% of questions	82.0%	84.0%
SimpleQA Verified (Epoch AI)reported	Correct answers% of questions	45.1%	73.9%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.