LLM benchmark scores, with the gaps filled

benchgap is an LLM benchmark leaderboard that fills in the missing scores. Most models are only ever run on a handful of benchmarks, so benchgap calibrates benchmarks against each other on the models measured on both, then estimates each missing score with its cross-validated error and a confidence level. Measured and estimated scores are always marked apart.

As of 2026-10-07: 401 models, 147 benchmark versions, 4892 measured and 16443 estimated scores (2500 high, 5182 medium and 8761 low confidence). Measured scores come from public leaderboards (artificial-analysis, published, vals-ai).