Anthropic models lead all three domains, with Claude Fable 5.1 (Max) first in Code and Work, and Claude Sonnet 5.5 (Max) leading Chat. OpenAI's GPT 6 Astra (Max) placed in the top four across all categories.
Arena.ai says OpenAI’s GPT-6.1 can now be tested in Agent Arena, where scores are still to come, and in Code Arena for WebDev, Text, Vision, Search, and Document. OpenAI says GPT-6.1 Sol offers near-Astra intelligence for a fifth of the price.
Arena.ai now places OpenAI’s GPT-6 Luna (Max) on the Agent Arena Pareto frontier at +1.59% net improvement and a $0.05 median cost per task. It costs 29% less than DeepSeek-V4.1-Flash and 76% less than Hy4 preview, trailing those scores by 2.27 and 2.51 percentage points.
Arena.ai reports a +1.6% net improvement for OpenAI’s GPT-6 Luna (Max) across 8,000 real-world agentic sessions, at a $0.05 median cost per task. It did not reach the Agent Arena Pareto frontier.
Arena.ai has added Claude Sonnet 5.5 by AnthropicAI to Agent Arena and to Battle Mode for WebDev, Text, Vision, and Document. Claude says it is the second Claude 5.5 model, runs more than 30% faster than Sonnet 5, and costs up to 30% less for most work.
Arena.ai ranks Claude Opus 5.5 (High) No. 2 in Agent Arena, with a +12.15% net improvement at a $1.31 median cost per task. It scores above Opus 5 (Max) and Opus 5 (High) while costing 40–56% less.
Arena.ai places Anthropic’s Claude Opus 5.5 (High) second in Agent Arena with a +12.15% net improvement. Only Fable 5.1 (Max) ranks higher, and Arena.ai puts the median price at $1.31 per task, 64% less.
Arena.ai says OpenAI’s GPT-6 Sol (Max) recorded a +7.7% net improvement across 4,000+ real-world agentic sessions, at a median cost of $0.75 per task. It trails Claude Fable 5 (High) by 0.60 percentage points while costing 56% less per task.
Arena.ai reports a +7.7% net improvement and sixth place for GPT-6 Sol (Max) across 4,000+ real-world agentic sessions. Versus GPT-5.6 Sol (xHigh), that is up from +6.2% and eighth, at half the per-token price.
Arena.ai places SpaceXAI’s Grok 4.7 (xHigh) 16th in Agent Arena with a +3.96% net improvement, at a median cost of $1.14 per task, above Grok 4.6 (High) and Grok 4.5.
OpenAI’s GPT-6 Sol and GPT-6 Luna can now be tested in Arena.ai’s Agent Arena, with scores still to come, and in Code Arena for WebDev, Text, Vision, Search, and Document. OpenAI says the models build on GPT-6 Astra and that their API prices are 50% lower than GPT-5.6 promotional pricing.
Arena.ai has added Claude Opus 5.5 to Agent Arena and to Battle Mode for WebDev, Text, Vision, and Document. Claude says it is the first Claude 5.5 model, performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
