AI BriefingGemini 4 Argon (High) Scores 53 on Artificial Analysis Intelligence Index
Key point
The proprietary reasoning model costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1M token context window.
Details
Intelligence and Performance
Gemini 4 Argon (High), a proprietary reasoning model released by Google in September 2026, scores 53 on the Artificial Analysis Intelligence Index. This places it 8th out of 223 models in its class and well above the median score of 26 for comparable reasoning models. The model supports both text and image input and outputs text.
Pricing and Availability
The model is available via API through one provider with the following pricing structure:
- Input: $2.00 per 1M tokens
- Output: $10.00 per 1M tokens
- Cache Discount: 95%
- Blended Price: $1.47 per 1M tokens (based on a 7:2:1 cache hit/input/output ratio)
Technical Specifications
- Context Window: 1M tokens
- Reasoning: Enabled
- Parameters: Not disclosed
- Verbosity: Generated 110M output tokens during the Intelligence Index evaluation, which is higher than the median of 82M for its class.
Benchmark Context
The Artificial Analysis Intelligence Index evaluates models across reasoning, knowledge, mathematics, and coding using 10 specific benchmarks, including AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, and Humanity's Last Exam. Gemini 4 Argon (High) is positioned as a leading model in intelligence relative to its price point.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Google Announces Gemini 4 Argon with 1M Token Output and Cybersecurity FocusInception Releases Ultra-Fast LLM 'Mercury 2.5' Generating 770 Tokens Per Second
GLM-5.3-Flash Matches Specialized Decision Models in Zero-Shot Classification via Logit Extraction