Three benchmarks name different top AI models: Gemini 4 Argon, Claude Opus 5.5, GPT-6.1 Sol
Three evaluation methods produced three different leaders among new AI models released this week. On LMSYS Chatbot Arena, which aggregates human preference votes, Google's Gemini 4 Argon leads with 1,525 points, followed by Meta's Muse Wonder at 1,513 and Anthropic's Claude Opus 5.5 at 1,508. Arena marks Gemini 4 Argon's score as provisional with a ±9 range based on roughly 4,900 votes.
Key points
- Arena human voting: Gemini 4 Argon 1,525 pts, Muse Wonder 1,513, Claude Opus 5.5 1,508
- Artificial Analysis test scores: Claude Opus 5.5 leads at 58 pts; Gemini 4 Argon ties at 53 pts
- Cost per run: GPT-6.1 Sol ~$0.32 vs Claude Opus 5.5 ~$5.98; MiMo-V2.6-Pro ~$0.13 open weights
Artificial Analysis, which runs standardized test suites including Humanity's Last Exam and Terminal-Bench, ranks Claude Opus 5.5 (max settings) first with 58 points. Claude Sonnet 5.5 and Muse Wonder Full tie at 56, while Gemini 4 Argon, GPT-6 Astra, and Claude Fable 5.1 share 53 points.
On cost per test run, OpenAI's GPT-6.1 Sol (high settings, 50 points) costs about $0.32, far below Claude Opus 5.5's $5.98. Xiaomi's MiMo-V2.6-Pro (46 points) costs roughly $0.13 and is released under the MIT license with open weights. Gemini 4 Argon API pricing starts at $2 per million input tokens and $10 per million output tokens until November 30, then rises to $4 and $20.
Model pages: Gemini 4 Argon → · Muse Wonder → · Claude Opus 5.5 →
The story so far
7 episodes →- Three benchmarks name different top AI models: Gemini 4 Argon, Claude Opus 5.5, GPT-6.1 Solthis story
When measuring the 'strongest AI' with 3 yardsticks, the #1 was different for each. Gemini 4 Argon, Claude Opus 5.5, and GPT-6.1 Sol
note.com · 14 October 2026
Loading the full article…
This text was published by note.com and written by めぐみ 転職×AI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Nvidia launches Nemotron 3.5 Super VL and Bolt models for enterprise agents and AI PCs · 2 src
- Google unveils Gemini 4 Argon with million-token output window · 3 src
- Google makes Gemini 4 Argon generally available to AI Pro and Ultra subscribers · 38 src
- The Truth Behind 'Apple and Meta Team Up on AI': It's Not Siri, It's Mac Studio | A Manager's Breakdown of Confirmed Facts, Reports, Unannounced Details, and Im · 2 src
- Elevenlabs launches two realtime speech-to-speech models for AI conversations · 1 src
Comments
via GitHub Discussions