Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
InternLM-Mathgithub.comInternLM Math is a state-of-the-art bilingual open-source math reasoning LLM that functions as a solver, prover, verifier, and augmentor. It achieves top performance on both informal math benchmarks (MATH, GSM8K) and formal theorem proving (MiniF2F) across multiple model sizes.
Parse Score
