⌕Is ___ SOTA?

Benchmark health

NameStatusSaturationLast result
LMArena Text (style-controlled, overall)activeunknown—
LMArena Text (style-controlled, coding)activeunknown—
LMArena Text (style-controlled, math)activeunknown—
LMArena Text (style-controlled, hard prompts)activeunknown—
LMArena Text (style-controlled, longer query)activeunknown—
LMArena Vision (style-controlled)activeunknown—
LMArena WebDevactiveunknown—
LMArena Text-to-Imageactiveunknown—
LMArena Text-to-Videoactiveunknown—
LMArena Image Editactiveunknown—
LMArena Text factualityactiveunknown—
GPQA Diamondactiveunknown—
FrontierMathactiveunknown—
LiveBenchactiveunknown—
SimpleQA Verifiedactiveunknown—
Terminal-Bench 2.0activeunknown—
Terminal-Bench 4.0activeunknown—
SWE-bench Pro V2 HARDactiveunknown—
Humanity's Last Examactiveunknown—
GDP.pdfactiveunknown—
MTEB Multilingual v2 (MMTEB)activeunknown—
MTEB English v2activeunknown—
Open ASR Leaderboard (English short-form)activeunknown—
Artificial Analysis Intelligence Indexactiveunknown—
Artificial Analysis Coding Indexactiveunknown—
Artificial Analysis Agentic Indexactiveunknown—
Artificial Analysis Speech Arenaactiveunknown—
SWE-bench Verifieddisplay_onlysaturated—
Aider Polyglotactiveunknown—
ARC-AGIactiveunknown—
Fiction.liveBench 120kactiveunknown—
METR Time Horizonsdisplay_onlyunknown—