WHAT NEW IN X11.04 WED

AI collections from X · 22 collections · 67,905 posts

benchmarkIMAGE

Leaked Gemini 4 Pro benchmarks claim it beats GPT-6 Astra on several tests

Unconfirmed Gemini 4 Pro specs and benchmarks have surfaced, including a 2M token context and 95.3% on Terminal-Bench, with claims it beats GPT-6 Astra on several tests.

Shub
@shub0414Archived 2026.09.19Originally posted 2026.09.18
Leaked Gemini 4 Pro benchmarks claim it beats GPT-6 Astra on several tests
Shub @shub0414Originally posted 2026.09.18
Open original on X

Gemini 4 Pro benchmarks just leaked and if this is real, Google is coming for the AI throne. The specs look insane: → 2M token context → 256K output reportedly being tested → $2.25 / 1M input → $11.25 / 1M output → 95.3% Terminal-Bench 2.1 → 88.7% DeepSWE v1.1 → 86.8% OSWorld-2.0 → 94.7% CharXiv Reasoning And reportedly beating GPT-6 Astra on several leaked benchmarks. Nothing is officially confirmed yet but this could get very interesting.

This post quotes another post: “New Gemini 4 Pro benchmark scores too large to render, user jokes”

x.com/shub0414/status/2100954711600046422Archived 2026.09.19 10:30