Gemini 4 Argon and Muse Wonder on HLE-Diamond.
Gemini 4 Argon competes with GPT-6.1 Sol and Opus 5.5, but uses ~5x more output tokens than GPT-6 models.
GPT-6.1 Sol and Opus 5.5 results on CheatBench.
GPT-6.1 Sol (an improvement over GPT-6 Sol) has a higher cheating rate than Muse Spark 1.3 and Claude Opus 5.5.
We are releasing HLE-Diamond, a refined subset of Humanity’s Last Exam (HLE), shaped by a year of refinement and input from various research communities.
Release notes: lastexam.ai/blog/hle-diamo…
