Mercor, the AI evaluation company behind the APEX benchmarks, found that 90% of US working hours involve tasks poorly covered by the 29 AI benchmarks it studied.
This resonates with my experience using Muse for shopping and ChatGPT for understanding my priorities.
Neither is reflected well in popular benchmarks. https://www.mercor.com/research/labor-index/benchmark-map/
Dare Obasanjo
npub1t7…ydsf2
2026-10-17 16:48:50 UTC
Author Public Key
npub1t7rr7j99rwt57zrqnfd9sxxcmpy034647rmp2k22vfk6gugm0rfqaydsf2Seen on
wss://relay.momostr.pinkPublished at
2026-10-17 16:48:50 UTCEvent JSON
{
"id": "7b4e4cec18f73191ce595a526b91660423a89dc3099719ce35c5078aab232026",
"pubkey": "5f863f48a51b974f08609a5a5818d8d848f8d755f0f615594a626da4711b78d2",
"created_at": 1792255730,
"kind": 1,
"tags": [
[
"proxy",
"https://mas.to/@carnage4life/117457271559068427",
"web"
],
[
"proxy",
"https://mas.to/users/carnage4life/statuses/117457271559068427",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://mas.to/users/carnage4life/statuses/117457271559068427",
"pink.momostr"
],
[
"-"
]
],
"content": "Mercor, the AI evaluation company behind the APEX benchmarks, found that 90% of US working hours involve tasks poorly covered by the 29 AI benchmarks it studied.\n\nThis resonates with my experience using Muse for shopping and ChatGPT for understanding my priorities.\n\nNeither is reflected well in popular benchmarks. https://www.mercor.com/research/labor-index/benchmark-map/",
"sig": "a685cc43f4c32d8806d559341c73aedfce1758ea73b21cff76fd03224384a71b260b2cdeec0e848c29bc066ce95809960915f03e7495db596c1ba0031f6ea37f"
}