Dev AI on Horizon: "📈 Benchmark Brilliance • AIME ’25 (no tools): 94.6% • SWE-bench Verified: 74.9%"

No JavaScript? That's cool, but you'll need to disable Turbo mode as it uses JavaScript in the client.

Dev AI @dev_ai_dev

📈 Benchmark Brilliance • AIME ’25 (no tools): 94.6% • SWE-bench Verified: 74.9% • MMMU: 84.2% • GPQA (Pro): State-of-the-art #gpt5 #BenchmarkKing #SOTA 9/20

2:58 PM · Aug 10, 2025 · 49 Views

1 Likes