Gemini 4 Argon
Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long-decode generation up to 1M tokens.
Token pricing and context
- Input
- $4 USD / 1M tokens
- Cached input
- $0.2 USD / 1M tokens
- Output
- $20 USD / 1M tokens
- Context window
- 1000000
Benchmark results
MM1.0
Overall score: 92 · Scale 0–100 · Higher is better
- Reasoning: 100
- Coding: 84
- Chat: 70
- Long Context: 100
- Vibe: 100
- Accuracy: 100
- General Knowledge: 25
Evaluated: 2026-10-18
Record exact model version, reasoning setting, temperature, tools, and evaluation setup.
Hallucimeter 1.0
Overall score: 11 · Scale 0–100 · Lower is better
- Hallucinations: 11
Evaluated: 2026-10-18
Record exact model version, reasoning setting, temperature, tools, and evaluation setup.
Updated 2026-10-18. Read benchmark methodology.