AI Rankings
200+ current models — Claude, GPT, Gemini, Grok, DeepSeek, Qwen and more — on their published benchmark scores, each linked to its source, plus what each API provider charges to run them.
Most scores come from Artificial Analysis; Epoch AI, MathArena, benchmark leaderboards and the model makers themselves (marked v) add the rest. QAI's own measurements live in EdgeBench.
GPQA DiamondHumanity's Last ExamTerminal-BenchAPEX-Agentsτ²-Bench