Simon Willison on Nostr: OK, this is exciting: we now have four alternatives with benchmarks that put them in ...
OK, this is exciting: we now have four alternatives with benchmarks that put them in the same class as GPT-4 - up from zero contenders less than a month ago
Claude 3 Opus, Gemini 1.5, Mistral Large and now Inflection-2.5:
https://simonwillison.net/2024/Mar/8/inflection-25/Looks like the GPT-4 barrier has been well and truly smashed
Published at
2024-03-08 01:04:06Event JSON
{
"id": "d121619243c985f4ca49e784136a04e45d99618f6a3075977694a6fab907e29e",
"pubkey": "8b0be93ed69c30e9a68159fd384fd8308ce4bbf16c39e840e0803dcb6c08720e",
"created_at": 1709859846,
"kind": 1,
"tags": [
[
"e",
"491d1cf3bba2195102ab345231334cbffdf99ad232018e6abbe8dac76ea4c178",
"wss://relay.mostr.pub",
"reply"
],
[
"proxy",
"https://fedi.simonwillison.net/users/simon/statuses/112057374928803744",
"activitypub"
]
],
"content": "OK, this is exciting: we now have four alternatives with benchmarks that put them in the same class as GPT-4 - up from zero contenders less than a month ago\n\nClaude 3 Opus, Gemini 1.5, Mistral Large and now Inflection-2.5: https://simonwillison.net/2024/Mar/8/inflection-25/\n\nLooks like the GPT-4 barrier has been well and truly smashed",
"sig": "f0fa8cc5ae486aac5f65286c96e836deaf9bb14c8f8d62122522496b277fa2607ed3174b07791b12f7b6a08d7a3a82d62666d0990184fdabed6dd7b585fed60d"
}
