AI Benchmark Leaderboard

Live rankings of frontier language models across five public benchmarks.

Filters

Rank	Model	Overall Score	Category	Updated	Select

Benchmark Data Explorer

Dig into per-benchmark results, distributions and task-level outcomes.

Filters

Score Distribution

All evaluated models, MMLU (%)

Summary

Models

128

Mean Score

—

Median Score

—

Task Results (MMLU)

Tick two or more models to compare them head-to-head.

	Rank	Model	Score	Percentile	Relative

Select a model result to view details.

Provider: Example Labs

Released: Apr 20, 2024

Context: 128K · Parameters: 70B

Overall Rank

1

Overall Score

92.4

Benchmark Breakdown

Tap any row to open it in the data explorer.

Benchmark	Score	Rank	Percentile	vs. field

Side-by-side scores across every tracked benchmark.

Compared models

Overall Score Comparison

Weighted overall score (0–100)

Score by Benchmark

Best score per row is highlighted. Tap a model column for details.