Tested on 26 benchmarks with 47.7% average. Top scores: MATH level 5 (91.2%), HELM — IFEval (83.4%), Fiction.LiveBench (83.3%).
Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.
Computer-aided design evaluation. Tests understanding of CAD concepts, 3D modeling, and engineering design principles.
Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Stanford HELM evaluation of mathematical reasoning across diverse problem types.
- Typetext
- ContextN/A
- ReleasedJan 2024
- LicenseProprietary
- Statusbenchmark-only