Frontier Log

Benchmark

AutomationBench

0204060Oct 202641.4%GPT-6 Astra40.0%Opus 5.551.3%Gemini 4 Argon0204060Oct 202641.4%GPT-6 Astra40.0%Opus 5.551.3%Gemini 4 Argon

Results

ModelScoreSourceHuman-verified
Gemini 4 Argon30 Sep 2026 · Google51.3%Gemini 4 Argon: our next era of frontier intelligenceSource imageYes
Claude Opus 5.522 Sep 2026 · Anthropic40.0%Introducing Claude Opus 5.5run and reported by Zapier, without fallback modelsYes
GPT-6 Astra3 Sep 2026 · OpenAI41.4%GPT-6 Astra: A new generation of intelligenceYes

Benchmark

zapier.comHigher is better

All benchmarks