gemini-4IMAGE

Gemini 4 Argon benchmark scores surface, led by 99.7% on GraphWalks

The listed scores are Vals Index 68.9%, DeepSWE v1.1 77.9%, Vibe Code Bench 91.9%, RiemannBench 76.0% and GraphWalks 99.7%, with Argon said to lead Opus 5.5, GPT-6 Astra and Fable 5.1 on most of them.

Peng

@pengsonalArchived 28 days agoOriginally posted 2026.10.01

Gemini 4 Argon benchmark scores surface, led by 99.7% on GraphWalks

Peng @pengsonalOriginally posted 2026.10.01

Open original on X

GOOGLE LAUNCHED GEMINI 4 ARGON AND IT'S ALREADY BEATING OPUS 5.5, GPT-6 ASTRA AND FABLE 5.1 the benchmark numbers are wild: • Vals Index → 68.9% • DeepSWE v1.1 → 77.9% • Vibe Code Bench → 91.9% • RiemannBench → 76.0% • GraphWalks → 99.7% it leads on most of the benchmarks shown here

This post quotes another post: x.com/google/status/2105388143902175529

x.com/pengsonal/status/2105394165731529012Archived 2026.10.01 10:01