Gemini 4 Hydrogen debuts at No. 5 on Agent Arena with a net improvement of 14.8%
Google DeepMind's Gemini 4 Hydrogen (High) debuted on Agent Arena at No. 5, with a net improvement of 14.8% across 6.5k real agent sessions. The model is the fastest among the top 10, with a median time of 5.3 minutes per task—3 times faster than No. 1 Claude Fable 5.2 and 2.4 times faster than GPT-6 Astra; its median cost is $1.6 per task, 3.7 times cheaper than GPT-6 Astra and 4.7 times cheaper than Claude Fable 5.1, with API token pricing at $1.5 per million input tokens and $7.5 per million output tokens. By subcategory, it ranks No. 2 in controllability (+21%), No. 4 in positive feedback-to-complaint ratio (+32%), and No. 5 in confirmed success (+15%); by task category, it ranks No. 3 in Chat (+19%), No. 7 in Work (+13%), and No. 9 in Code (+12%).
Why read this
SelectedAI score 74
The leaderboard provides speed and cost comparisons, which can be used to judge the model's cost-effectiveness position in agent tasks.
Topics
View original postMeet Gemini 4 Hydrogen: built for rapid coding, multimodal synthesis, and everyday workflows. It finishes tasks 2.5x faster than 3.8 Flash and surpasses Argon on the @ArtificialAnlys Intelligence Index.
View original
Meet Gemini 4 Hydrogen: built for rapid coding, multimodal synthesis, and everyday workflows. It finishes tasks 2.5x faster than 3.8 Flash and surpasses Argon on the @ArtificialAnlys Intelligence Index.
Body
Gemini 4 Hydrogen (High) by @GoogleDeepMind debuts #5 on Agent Arena with +14.8% net improvement across 6.5k real-world agentic sessions.
Hydrogen stands out for its speed and cost efficiency: - Fastest model in the top 10: 5.3 min/task (median), 3x faster than #1 Claude Fable 5.2 and 2.4x faster than GPT-6 Astra - Cost-efficient: $1.6 cost/task (median), 3.7x cheaper than GPT-6 Astra and 4.7x cheaper than Claude Fable 5.1. API token pricing: $1.5/$7.5 input/output per million tokens Notably, it spends more output tokens per task: 41% more than Carbon, 2.8x more than Argon.
Strong across key signals: - #2 Steerability: +21% (behind only Fable 5.2 at +33%; ahead of Carbon at +19% and Opus 5.5 at +18%) - #4 Praise vs. Complaint: +32% - #5 Confirmed Success: +15%
Ranking by task category: - #3 in Chat: +19% - #7 in Work: +13% - #9 in Code: +12%
Hydrogen delivers competitive performance while completing tasks significantly faster and at a fraction of the cost of several leading models. Congrats to the @GoogleDeepMind team on another impressive release!