Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Scored from OpenAI's chatgpt-4o-latest API page (the alias for the GPT-4o snapshot used in ChatGPT; opened this run, now shut down): 128,000-token context = 1; text and image input = 3; $5 input / $15 output per 1M tokens = $7.50 blended at 3:1 = 2.75, rounded to 3 (the page shows the current list price; the August 2024 launch price was not separately opened). Reasoning, coding and speed are null: no Artificial Analysis index or Terminal-Bench figure was opened and OpenAI published no speed; OpenAI said granular benchmarking of this change is an open research problem. Press reported a Chatbot Arena score of 1314, 17 points above Gemini-1.5-Pro-Exp. Independent reviews: 3 found (Tom's Guide, Beebom, DailyAI press reports; no hands-on test of this exact update). developers.openai.com
Now, though, a new version of ChatGPT-4o (20240808) has reclaimed the lead from its rivals with a score of 1314 — 17 points ahead of Gemini-1.5-Pro-Exp.
On the LMSYS leaderboard, the new ChatGPT model has reclaimed the top spot with a score of 1314 points.
Announcing an updated ChatGPT-4o model yesterday was unlikely to have been a coincidence.
| OpenAI knocks Gemini off the top of chatbot leaderboard with its new model | Tom's Guide · Aug 14, 2024 | 0.60 |
|---|---|
| Gemini Live voice released and new ChatGPT-4o tops LMSYS | DailyAI · Aug 14, 2024 | 0.20 |
| ChatGPT Got a Secret Update Last Week, And It's Performing At Its Best | Beebom · Aug 16, 2024 | 0.70 |
Photos from readers, kept apart from the pin's sourced media. Rate what you ate or saw, and on a restaurant pin tag the dishes right on your photo.
The first entry is always the pin's source. Overall confidence is a weighted average of how firmly each reference supports the start and end times used above; a reference counts half as much for every 180 days older than the newest.
OpenAI's own model release notes date this entry August 12, 2024
Something missing or wrong? Say it in your own words: a link that backs this pin up, a different start or end date and why, or a fact it lacks or gets wrong. The AI checks it against this pin's sources, searches for better ones, and adds any page that backs you up. The pin's own sources still count most. A picture that shows something else, or shows it badly, is looked at too, and moved down or replaced.