Head to head
GPT-6 Astra leads on 1 of 1 shared benchmarks; Gemini 4 Argon is ~80% cheaper per blended million tokens.
GPT-6 Astra leads on 1 of 1 shared benchmarks; Gemini 4 Argon is ~80% cheaper per blended million tokens.
| Dimension | Gemini 4 Argon | GPT-6 Astra |
|---|---|---|
| Vals Index | 68.9% | — |
| GPQA Diamond | — | 96% |
| HLE | — | 54.7% |
| Terminal-Bench 2.1 | — | 89.9% |
| Terminal-Bench 4.0 | 57.4% | 57.9% |
| FrontierSWE v2 | 55% | — |
| DeepSWE v1.1 | 77.9% | — |
| Automation-Bench | 51.3% | — |
| OSWorld-2.0 | 69.2% | — |
| Chartography | 71.6% | — |
| GraphWalks | 84.2% | — |
| CWE-bench v1 | 68% | — |
| Agents' Last Exam | 39.5% | — |
| Blended price | $6.00 /1M | $30.00 /1M |
| Full priceInput · Output · Cached input | $2.00 · $10.00 · $0.100 | $10.00 · $50.00 · $1.00 |
| Context window | 1,048.576K | 1,050K |
Adjust the monthly volume — every model recomputes instantly.
Estimates use list prices and ignore cached input, batch discounts, and off-peak rates.