THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

THE HISTORICAL RECORD

Frontier
timeline.

Dated releases and milestones with direct provenance. Filters never merge incompatible benchmark scores.

2026-11-07 / benchmarks

Claude Fable 5.1 recorded coding score changed ↗

Anthropic · Source ↗

2026-11-07 / benchmarks

Claude Sonnet 5.5 recorded coding score changed ↗

Anthropic · Source ↗

2026-11-07 / benchmarks

Gemini 3.8 Flash recorded coding score changed ↗

Google · Source ↗

2026-11-07 / benchmarks

GPT-5.6 Terra recorded coding score changed ↗

OpenAI · Source ↗

2026-11-07 / benchmarks

GPT-6 Luna recorded coding score changed ↗

OpenAI · Source ↗

2026-11-07 / benchmarks

GPT-6.1 Sol recorded coding score changed ↗

OpenAI · Source ↗

2026-11-07 / benchmarks

Grok 4.6 recorded coding score changed ↗

xAI · Source ↗

2026-11-06 / models

Measuring how AI agents handle everyday wet-lab science ↗

OpenAI · Source ↗

2026-11-05 / models

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips ↗

Google · Source ↗

2026-11-05 / models

GPT‑6 Cyber: Advancing the frontier of aligned cybersecurity agents ↗

OpenAI · Source ↗

2026-11-05 / models

Transform a quick drawing into a live app with Gemini. ↗

Google · Source ↗

2026-11-04 / models

DevRev delivers autonomous self-service with GPT-6.1 Sol ↗

OpenAI · Source ↗

2026-10-29 / models

An updated Model Spec for more capable and beneficial AI ↗

OpenAI · Source ↗

2026-10-29 / models

How to use Gemini to update your resume ↗

Google · Source ↗

2026-10-29 / models

How we detect frontier model misalignment ↗

OpenAI · Source ↗

2026-10-29 / models

You can now generate, preview, and edit documents, PDFs, presentations, spreadsheets, and more directly in Gemini. ↗

Google · Source ↗

2026-10-28 / models

Dive into new topics with immersive explorations in the Gemini app. ↗

Google · Source ↗

2026-10-28 / models

Gemini 4 Carbon: our next frontier model ↗

Google · Source ↗

2026-10-27 / models

8 examples of Gemini 4 Argon in action ↗

Google · Source ↗

2026-10-27 / models

Retell uses OpenAI models to help power 100M monthly calls ↗

OpenAI · Source ↗

2026-10-26 / models

15 college students share their favorite Gemini features ↗

Google · Source ↗

2026-10-26 / models

GPT-6.1 Sol helps CodeRabbit strengthen security across complex codebases ↗

OpenAI · Source ↗

2026-10-26 / models

Greptile takes bug detection beyond code review with GPT-6 Astra ↗

OpenAI · Source ↗

2026-10-26 / models

Introducing GPT-6.1 Terra ↗

OpenAI · Source ↗

2026-10-23 / models

Anima helps clinics cut call waits by 75% with GPT-6 and GPT-Live ↗

OpenAI · Source ↗

2026-10-23 / models

Securing our frontier model training environment ↗

OpenAI · Source ↗

2026-10-23 / models

See what 5 builders are making with Gemini 4 Argon ↗

Google · Source ↗

2026-10-22 / models

Build more responsive apps with the Decisions API ↗

OpenAI · Source ↗

2026-10-21 / models

OpenAI models are coming to Google Cloud ↗

OpenAI · Source ↗

2026-10-21 / models

Patch the Planet: global response coordination as agents uncover critical vulnerabilities ↗

OpenAI · Source ↗

2026-10-21 / models

Using thousands of AI agents to uncover new leads in biological data ↗

OpenAI · Source ↗

2026-10-20 / models

New Gemini tools for small business owners ↗

Google · Source ↗

2026-10-20 / models

Terminal X matches senior investor judgment 88.6% with GPT-6.1 ↗

OpenAI · Source ↗

2026-10-19 / models

4 tips for styling outfits with Gemini ↗

Google · Source ↗

2026-10-19 / models

Advancing coding in low‑resource programming languages ↗

OpenAI · Source ↗

2026-10-16 / models

Stack Overflow for Agents triples signups with ChatGPT plugin ↗

OpenAI · Source ↗

2026-10-15 / models

Bringing GPT-Rosalind to academic research labs ↗

OpenAI · Source ↗

2026-10-14 / models

Amp puts AI agents to work beyond code with OpenAI models ↗

OpenAI · Source ↗

2026-10-14 / models

How Third Moment Research runs 10,000 agents for 36+ hours ↗

OpenAI · Source ↗

2026-10-13 / models

Developing Gemini 4 Argon responsibly and safely ↗

Google · Source ↗

2026-10-13 / models

Gemini 4 Argon comes to the Gemini app. ↗

Google · Source ↗

2026-10-13 / models

Gemini 4 Argon is now available for developers. ↗

Google · Source ↗

2026-10-13 / models

Gemini 4 Argon: Built to solve your hardest problems ↗

Google · Source ↗

2026-10-12 / models

Muse Wonder Full released ↗

Meta · Source ↗

2026-10-12 / models

Muse Wonder released ↗

Meta · Source ↗

2026-10-09 / models

Asana cuts model costs 76x in browser tests with GPT-6.1 Sol ↗

OpenAI · Source ↗

2026-10-07 / models

GPT-6 and Intelligent UI for everyone ↗

OpenAI · Source ↗

2026-10-02 / models

A model guide for the GPT-6 family ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

Claude Fable 5.1 recorded coding score changed ↗

Anthropic · Source ↗

2026-10-02 / benchmarks

Claude Opus 5.5 recorded coding score changed ↗

Anthropic · Source ↗

2026-10-02 / benchmarks

DeepSeek V4 Pro recorded coding score changed ↗

DeepSeek · Source ↗

2026-10-02 / benchmarks

DeepSeek V4.1 Flash recorded coding score changed ↗

DeepSeek · Source ↗

2026-10-02 / benchmarks

Gemini 3.1 Pro Preview recorded coding score changed ↗

Google · Source ↗

2026-10-02 / benchmarks

Gemini 3.5 Flash recorded coding score changed ↗

Google · Source ↗

2026-10-02 / benchmarks

Gemini 3.6 Flash recorded coding score changed ↗

Google · Source ↗

2026-10-02 / benchmarks

Gemini 3.7 Flash recorded coding score changed ↗

Google · Source ↗

2026-10-02 / benchmarks

Gemini 3.8 Flash recorded coding score changed ↗

Google · Source ↗

2026-10-02 / benchmarks

GPT-5.6 Luna recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

GPT-5.6 Sol recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

GPT-5.6 Terra recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

GPT-6 Astra recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

GPT-6 Luna recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

GPT-6 Sol recorded coding score changed ↗

OpenAI · Source ↗

2026-10-02 / benchmarks

Grok 4.5 recorded coding score changed ↗

xAI · Source ↗

2026-10-02 / benchmarks

Grok 4.6 recorded coding score changed ↗

xAI · Source ↗

2026-10-01 / benchmarks

Claude Fable 5.1 recorded coding score changed ↗

Anthropic · Source ↗

2026-10-01 / benchmarks

Claude Opus 5.5 recorded coding score changed ↗

Anthropic · Source ↗

2026-10-01 / models

gpt-4.1 now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-4.1-mini now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-4.1-nano now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5 now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5-mini now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5-nano now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5.1 now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5.2 now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5.4-mini now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / models

gpt-5.4-nano now listed in official pricing ↗

OpenAI · Source ↗

2026-10-01 / benchmarks

GPT-6 Astra recorded coding score changed ↗

OpenAI · Source ↗

2026-10-01 / benchmarks

GPT-6 Sol recorded coding score changed ↗

OpenAI · Source ↗

2026-10-01 / models

Guided Vision in Gemini Live: built for accessibility ↗

Google · Source ↗

2026-09-29 / models

GPT-6.1 Sol released ↗

OpenAI · Source ↗

2026-09-28 / models

Claude Sonnet 5.5 released ↗

Anthropic · Source ↗

2026-09-22 / models

Claude Opus 5.5 released ↗

Anthropic · Source ↗

2026-09-22 / models

GPT-6 Sol and Luna added to the API ↗

OpenAI · Source ↗

2026-09-10 / models

DeepSeek V4.1 Flash released ↗

DeepSeek · Source ↗

2026-09-03 / models

GPT-6 Astra released ↗

OpenAI · Source ↗

2026-09-02 / models

Gemini 3.8 Flash released ↗

Google · Source ↗

2026-09-01 / models

Claude Fable 5.1 released ↗

Anthropic · Source ↗

2026-08-13 / models

DeepSeek V4 Pro released ↗

DeepSeek · Source ↗

2026-08-13 / models

Gemini 3.7 Flash released ↗

Google · Source ↗

2026-08-12 / models

Grok 4.6 released with published agent evaluations ↗

xAI · Source ↗

2026-07-21 / models

Gemini 3.5 Flash-Lite released ↗

Google · Source ↗

2026-07-21 / models

Gemini 3.6 Flash released ↗

Google · Source ↗

2026-07-09 / models

GPT-5.6 Luna released ↗

OpenAI · Source ↗

2026-07-09 / models

GPT-5.6 Sol released ↗

OpenAI · Source ↗

2026-07-09 / models

GPT-5.6 Terra released ↗

OpenAI · Source ↗

2026-05-19 / models

Gemini 3.5 Flash released ↗

Google · Source ↗

2026-05-04 / quantum

IBM reports Heron r3 performance ↗

Verified source · Source ↗

2026-04-28 / models

Mistral Medium 3.5 released ↗

Mistral · Source ↗

2026-03-16 / models

Mistral Small 4 released ↗

Mistral · Source ↗

2026-03-03 / gear

Apple announces M5 Max ↗

Verified source · Source ↗

2026-03-03 / gear

M5 Max released ↗

Apple · Source ↗

2026-02-19 / models

Gemini 3.1 Pro Preview released ↗

Google · Source ↗

2025-12-02 / models

Mistral Large 3 released ↗

Mistral · Source ↗

2025-10-15 / models

Claude Haiku 4.5 released ↗

Anthropic · Source ↗

2025-04-05 / models

Llama 4 Maverick released ↗

Meta · Source ↗

2025-04-05 / models

Llama 4 Scout released ↗

Meta · Source ↗

2025-03-06 / gear

Radeon RX 9070 XT released ↗

AMD · Source ↗

2025-01-30 / gear

GeForce RTX 5090 released ↗

NVIDIA · Source ↗

2024-12-09 / quantum

Willow: Google announced below-threshold error-correction results on Willow. ↗

google-quantum-ai · Source ↗