Gemini 4 Hydrogen scores 54 on Artificial Analysis Intelligence Index, just below Claude Sonnet 5.5 and GPT-6.1 Sol
Artificial Analysis reports that Google's Gemini 4 Hydrogen scores 54 on its Intelligence Index, just below Claude Sonnet 5.5 and GPT-6.1 Sol. It costs a third of Sonnet's cost but about 2.5x that of GPT-6.1 Sol, and adds an xhigh reasoning level.
Google's Gemini 4 Hydrogen scores 54 on the Artificial Analysis Intelligence Index, placing it just below Claude Sonnet 5.5 and GPT-6.1 Sol, according to Artificial Analysis (@artificialanlys).
Key figures
- Intelligence Index score: 54 for Gemini 4 Hydrogen, per Artificial Analysis.
- Ranking: Just below Claude Sonnet 5.5 and GPT-6.1 Sol.
- Cost versus Claude Sonnet 5.5: Artificial Analysis puts Gemini 4 Hydrogen at a third of Sonnet's cost.
- Cost versus GPT-6.1 Sol: About 2.5x that of GPT-6.1 Sol.
- New reasoning level: Gemini 4 Hydrogen introduces an xhigh reasoning level.
Release cadence
Artificial Analysis says Google DeepMind has released its third new model in six weeks, with Gemini 4 Hydrogen the latest.
Context window, per-token pricing, parameter count and training cutoff are not given in the summary of Artificial Analysis' post, so none are listed here.
What this means
On Artificial Analysis' Intelligence Index, Gemini 4 Hydrogen sits close to the two models it trails, Claude Sonnet 5.5 and GPT-6.1 Sol. Its cost falls between them: a third of Sonnet's cost, but about 2.5x that of GPT-6.1 Sol. For teams comparing models on the index, that makes cost relative to GPT-6.1 Sol the main trade-off against Gemini 4 Hydrogen's score, while the comparison with Claude Sonnet 5.5 favors Gemini on cost. The addition of an xhigh reasoning level gives Gemini 4 Hydrogen a higher setting than the reasoning levels Google previously offered, though Artificial Analysis' summary does not detail how that level affects the score or cost.
Related Articles
Scale AI and IMDA launch SG-LegalClarify, testing 19 models on 1,860 Singapore law scenarios
Scale AI and Singapore's Infocomm Media Development Authority (IMDA) introduced SG-LegalClarify on November 12, 2026. The benchmark tests 19 language models on 1,860 scenarios across 10 domains of Singapore law, measuring both legal accuracy and whether models ask for missing facts before answering.
No model among 23 reaches 80% threshold on Vals AI and NextLadder Access to Justice Benchmark
NextLadder Ventures and Vals AI announced the Access to Justice Benchmark on November 10, 2026. None of the 23 models tested reached the 80% threshold for a reliable first point of contact across 252 legal-aid scenarios.
Anthropic's Fable 5.2 tops Remote Labor Index at 41.3%, completing real freelance jobs at professional quality
Anthropic's Fable 5.2 scores 41.3 percent on the Remote Labor Index from Scale Labs and the Center for AI Safety, which measures how often AI agents complete real freelance jobs well enough for a client to accept. The next-best systems, Opus 5.5 and GPT 6 Astra, score 21.25 and 20.83 percent. The top score at the benchmark's launch about a year ago was 2.5 percent.
Co-Design Bench: best coding agent fully solves only 26.4% of real user change requests
Researchers from Alibaba and several Asian universities released Co-Design Bench, a coding-agent test built from real user change requests. According to the paper, the best of ten models, GPT-6 Astra, meets about 70 percent of a task's requirements on average but is fully correct on only 26.4 percent of tasks.
Comments
Loading...