?
isitsota
Categories
Timeline
Compare
Changelog
Methodology
API
MCP
Badges
Alerts
⌕
Is
___
SOTA?
Benchmark
health
Name
Status
Saturation
Last result
LMArena Text (style-controlled, overall)
active
unknown
—
LMArena Text (style-controlled, coding)
active
unknown
—
LMArena Text (style-controlled, math)
active
unknown
—
LMArena Text (style-controlled, hard prompts)
active
unknown
—
LMArena Text (style-controlled, longer query)
active
unknown
—
LMArena Vision (style-controlled)
active
unknown
—
LMArena WebDev
active
unknown
—
LMArena Text-to-Image
active
unknown
—
LMArena Text-to-Video
active
unknown
—
LMArena Image Edit
active
unknown
—
LMArena Text factuality
active
unknown
—
GPQA Diamond
active
unknown
—
FrontierMath
active
unknown
—
LiveBench
active
unknown
—
SimpleQA Verified
active
unknown
—
Terminal-Bench 2.0
active
unknown
—
Terminal-Bench 4.0
active
unknown
—
SWE-bench Pro V2 HARD
active
unknown
—
Humanity's Last Exam
active
unknown
—
GDP.pdf
active
unknown
—
MTEB Multilingual v2 (MMTEB)
active
unknown
—
MTEB English v2
active
unknown
—
Open ASR Leaderboard (English short-form)
active
unknown
—
Artificial Analysis Intelligence Index
active
unknown
—
Artificial Analysis Coding Index
active
unknown
—
Artificial Analysis Agentic Index
active
unknown
—
Artificial Analysis Speech Arena
active
unknown
—
SWE-bench Verified
display_only
saturated
—
Aider Polyglot
active
unknown
—
ARC-AGI
active
unknown
—
Fiction.liveBench 120k
active
unknown
—
METR Time Horizons
display_only
unknown
—