gemini-4IMAGE
Gemini 4 Argon tops 13 of 19 benchmarks but trails on agentic coding
Google's own table shows Argon leading 13 of 19 benchmarks at $2/$10 pricing with 1M output tokens, but it comes last on Terminal-Bench 4.0 and FrontierSWE behind GPT-6 Astra, Fable 5.1 and Opus 5.5.
aipulsedaily
@aipulseda1lyArchived 28 days agoOriginally posted 2026.10.01
aipulsedaily @aipulseda1lyOriginally posted 2026.10.01
Gemini 4 Argon just dropped and it tops 13 of 19 benchmarks in Google's own table. $2 in and $10 out intro pricing, and a 1M token output limit, up from 64K. But it comes in dead last on Terminal-Bench 4.0 and FrontierSWE, the agentic coding tests, behind GPT-6 Astra, Fable 5.1 and Opus 5.5. We all seen this before where they destroy a benchmark but it doesnt perform in agentic or real world tasks. Its not out yet. Trusted cyber defenders get it first, then paid API and Google AI Ultra. Well see what happens on my NYC test.
x.com/aipulseda1ly/status/2105392022945149299Archived 2026.10.01 10:01