aiqbench · LLM benchmarks

Benchmarks

Per-axis LLM benchmarks. One leaderboard, one number, one source — no fabricated composites.

Sources: 8
Entries tracked: 22,308
Last sync: 49 min49 minutes ago

All sources syncing normally

Arena · Text· 10 hours ago
Arena · WebDev· 10 hours ago
Arena · Vision· 10 hours ago
Arena · Agent· 10 hours ago
GPQA Diamond· 49 minutes ago
SWE-bench· 49 minutes ago
Terminal-Bench· 49 minutes ago
ARC-AGI-2· 49 minutes ago

Arena · Text· 10 hours ago
Arena · WebDev· 10 hours ago
Arena · Vision· 10 hours ago
Arena · Agent· 10 hours ago
GPQA Diamond· 49 minutes ago
SWE-bench· 49 minutes ago
Terminal-Bench· 49 minutes ago
ARC-AGI-2· 49 minutes ago

Filter this table

Jump to a model's profile

Filter by org:

Released:AfterBefore

One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.

Axes22 on

Ranking on 22 axes — weighted blend, coverage-shrunk.

same = ranks models almost identically to an axis you already selected · close = nearly so · ? = too few shared models to tell.

Overall

Ability

Industry

Arena boards

Measured benchmarks

Agentic

Safety & factuality

Language

	Model	Org				Interval			Swing	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	i	Add to compare
No models match the current axes and filters.

Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model

The few things in AI and quantum that actually mattered this week — honestly summarised.