Benchmark
Deep Squeeze
A benchmark used to evaluate the programming or reasoning capabilities of AI models.
Timeline (last 90 days)
Sep 12
On the Deep Squeeze test, the old model scored 49%, while Gemini 3.7 Flash jumped to 65.3%.
Unverified50%
A benchmark used to evaluate the programming or reasoning capabilities of AI models.
On the Deep Squeeze test, the old model scored 49%, while Gemini 3.7 Flash jumped to 65.3%.