Vellum LLM Leaderboard: leaderboard

Clean comparison table of frontier models across MMLU, HumanEval, MATH, and other popular benchmarks.

Source: www.vellum.ai.

Benchmark results

Results are published separately for each benchmark or evaluation setting.

• Vellum - AIME 2025
• Vellum - ARC-AGI-2
• Vellum - GPQA
• Vellum - HumanEval
• Vellum - Humanity's Last Exam
• Vellum - LiveCodeBench
• Vellum - MATH
• Vellum - MMMLU

Interactive version: theaggregate.ai/benchmark?slug=vellum-llm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-21.