Gemini 4 Argon (High)
Benchmark scores, pricing, speed and comparisons for Gemini 4 Argon (High).
Gemini 4 Argon (High) is an AI model from Google, released 2026-09-30. It scores 50.4 on the Intelligence Index.
Gemini 4 Argon (High) at a glance
Google released Gemini 4 Argon (High) on September 30, 2026.
Gemini 4 Argon (High) scores 50.4 on the Intelligence Index, the overall score the AI Benchmark rankings sort models by. This score comes from independent third-party model evaluations, which Franklin AI syncs automatically each day.
It costs $4.00 per million input tokens and $20.00 per million output tokens, so a sample workload of 1 million input tokens and 200,000 output tokens costs about $8.00. It writes about 92 output tokens per second, so a 500-token answer takes roughly 5.5 seconds once output starts, after a wait of about 51.56 seconds for the first token.
The benchmark data has no Coding Index, Math Index or individual benchmark results for Gemini 4 Argon (High) yet.
Every pair of models in the catalogue has a head-to-head page. Pick Gemini 4 Argon (High) and a rival on the model comparisons page to compare their scores, prices and speed side by side.
Key scores
Claude Fable 5.2 (Max, Default Fallback) vs Gemini 4 Argon (High) benchmark comparisonClaude Fable 5.2Max, Default FallbackAnthropicGemini 4 ArgonHighGoogleClaude Fable 5.2 (Max, Default Fallback) vs Gemini 4 Argon (High) scores 64.6 and 50.4 on the captured intelligence index. Compare token rates and response timing.Gemini 4 Carbon (High) vs Gemini 4 Argon (High) benchmark comparisonGemini 4 CarbonHighGoogleGemini 4 ArgonHighGoogleGemini 4 Carbon (High) vs Gemini 4 Argon (High) scores 60 and 50.4 on the captured intelligence index. Compare token rates and response timing.Claude Opus 5.5 (Max, Default Fallback) vs Gemini 4 Argon (High) benchmark comparisonClaude Opus 5.5Max, Default FallbackAnthropicGemini 4 ArgonHighGoogleClaude Opus 5.5 (Max, Default Fallback) vs Gemini 4 Argon (High) scores 59.1 and 50.4 on the captured intelligence index. Compare token rates and response timing.
