aiqbench · LLM benchmarks

Benchmarks

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

Sources: 8
Entries tracked: 22,310
Last sync: 4 min4 minutes ago

All sources syncing normally

Arena · Text· 2 hours ago
Arena · WebDev· 2 hours ago
Arena · Vision· 2 hours ago
Arena · Agent· 2 hours ago
GPQA Diamond· 4 minutes ago
SWE-bench· 4 minutes ago
Terminal-Bench· 4 minutes ago
ARC-AGI-2· 4 minutes ago

Arena · Text· 2 hours ago
Arena · WebDev· 2 hours ago
Arena · Vision· 2 hours ago
Arena · Agent· 2 hours ago
GPQA Diamond· 4 minutes ago
SWE-bench· 4 minutes ago
Terminal-Bench· 4 minutes ago
ARC-AGI-2· 4 minutes ago

Filter this table

Jump to a model's profile

Filter by org:

Released:AfterBefore

Sonar Pro

75.5%

no interval published

perplexityswing #505–#505

Sonar

68.9%

no interval published

perplexityswing #563–#563

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.

Axes1 on

Ranking on 1 axis — single-board order, no blending.

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				± CI	Swing	Add to compare
128	Sonar Pro	perplexity	—	$3 / $15	75.5%	—	—
168	Sonar	perplexity	—	$1 / $1	68.9%	—	—

Showing MMLU-Pro (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.

Sonar Pro

Sonar

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