Arena shows side-by-side outputs from Claude Opus 5.5 and GPT-6 Sol

AArena.ai9/23/2026, 13:23:56

Arena.ai says it has generated side-by-side outputs on Arena from Anthropic’s Claude Opus 5.5 and OpenAI’s GPT-6 Sol.

Arena.ai says scores for Claude Opus 5.5 are coming soon. It says real-world tasks from its global user community power the Arena leaderboards.

#arena #claude-opus-5.5 #gpt-6-sol #model-evaluation

View original post ↗

Previous articleNVIDIA's Skill2Env compiles public Agent Skills into 7,971 terminal tasks Next articleLakebase Branching lets coding agents test database changes outside production

Related AI news

Arena.ai finds AI judges favor their own answers over human votes

Arena.ai compared 34,580 verdicts from 12 models with human votes across 1,460 Arena battles. On average, a model chose its own answer 58% of the time, while people chose that same answer 34% of the time.

AArena.ai•9/29/2026, 09:28:22•

#arena #ai-judges #model-evaluation #gpt-6-astra

Arena.ai opens GPT-6 Sol (Medium) in Direct Mode through Sept. 29 at 9am PT

OpenAI’s GPT-6 Sol (Medium) can be selected in Arena Direct Mode for the next 24 hours, through Sept. 29 at 9am PT. Arena.ai says it will remain available in Battle and Agent Mode after that window.

AArena.ai•9/28/2026, 08:58:34•

#gpt-6-sol #arena.ai #openai #direct-mode

Arena.ai places GPT-6 Sol (Max) sixth on Agent Arena at +7.7% and $0.75 per task

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.

AArena.ai•9/25/2026, 12:58:43•

#gpt-6-sol #agent-arena #openai #arena.ai #model-evaluation

Arena.ai launches redesigned Leaderboard Overview

The new overview gathers live signals on newly added models, category performance, capability notes, and Arena news, and can show cross-arena scores for models such as GPT-6 Sol and Claude Opus 5.5.

AArena.ai•9/24/2026, 13:39:55•

#arena.ai #leaderboard #model-evaluation #ai-products

Arena.ai ranks GPT-6 Sol (Max) fourth in Code Arena WebDev

Arena.ai reports that OpenAI’s GPT-6 Sol (Max) scored 1,689 points and placed fourth in Code Arena: WebDev, at a blended price of $8 per million tokens. It is 72 points above GPT-5.6 Sol (xHigh), while Arena.ai says GPT-6 Luna’s score is still pending.

AArena.ai•9/23/2026, 10:16:35•

#gpt-6-sol #arena.ai #code-arena #openai #webdev

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy