Gemini 4 Argon: benchmark results
Provider: Google. Access: API.
Unified ELO 2031 ± 23, rank #3 of 1608 rated models, from 69 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Briefcase | 64.63 | Rubric Pass Rate (%) | 100 |
| AA-Briefcase - DOCX - Rubric Pass Rate | 62.13 | Rubric Pass Rate (%) | 100 |
| AA-Briefcase - PDF - Rubric Pass Rate | 72.41 | Rubric Pass Rate (%) | 100 |
| AA-Briefcase - PPTX - Rubric Pass Rate | 67.36 | Rubric Pass Rate (%) | 100 |
| AA-Omniscience Index - Law | 53 | Omniscience Index | 100 |
| Agent Arena - Steerability | 15.88 | Steerability (%) | 100 |
| AutomationBench | 51.3 | Pass Rate (%) | 100 |
| AutomationBench-AA | 77.51 | Guardrail-Adjusted Objective Completion (%) | 100 |
| AutomationBench-AA - Finance - Raw Objective Completion | 94.62 | Raw Objective Completion (%) | 100 |
| AutomationBench-AA - HR - Raw Objective Completion | 81.99 | Raw Objective Completion (%) | 100 |
| AutomationBench-AA - Marketing - Raw Objective Completion | 94.66 | Raw Objective Completion (%) | 100 |
| AutomationBench-AA - Sales - Raw Objective Completion | 92 | Raw Objective Completion (%) | 100 |
Interactive version: theaggregate.ai/model?slug=gemini-4-argon · How It Works · Data refreshed daily, snapshot 2026-10-01.