artificialwatch

The best AI model right now is Claude Fable 5.2

Anthropic's model leads ArtificialWatch's combined ranking of 7 public leaderboards and is first on 6 of the 7 on its own. Next: Gemini 4 Carbon, then GPT-6 Astra.

boards read Nov 11 · 50 models ranked · computed from public scores, not our opinion · updated daily

Know when a new #1 ships →

#1 on each board

each board's own top score · read Nov 11

Claude Fable 5.2 is first on 6 of 7. On Artificial Analysis, Gemini 4 Carbon leads at 59.4; Claude Fable 5.2 is not scored there yet.

top 10, combined

bench index: median percentile across the boards that score each model
  1. 01Claude Fable 5.2Anthropic · 6 boards100$8 / $40
  2. 02Gemini 4 CarbonGoogle · 6 boards93.7$2 / $10
  3. 03GPT-6 AstraOpenAI · 7 boards92$10 / $50
  4. 04Claude Opus 5.5Anthropic · 7 boards90.9$4 / $20
  5. 05Claude Fable 5.1Anthropic · 5 boards88$10 / $50
  6. 06Claude Sonnet 5.5Anthropic · 7 boards83.3$2 / $10
  7. 07GPT-6.1 SolOpenAI · 7 boards81.5$2 / $10
  8. 08Gemini 4 ArgonGoogle · 7 boards80$2 / $10
  9. 09GPT-6.1 TerraOpenAI · 6 boards77.9$1 / $5
  10. 10Claude Opus 5Anthropic · 4 boards74.9$5 / $25

Price: per 1M input / output tokens on the maker's own API, as listed November 11, 2026. Every board's number for all 50 models: the full bench index. Every price: API prices. The data, free to reuse: CSV · JSON. Who held #1 before: every #1 since July, with dates.

most model per dollar

36 models with a published price
  1. Gemini 4 Carbon$4 blended · index 93.794% of the #1's index for 25% of its price
  2. GPT-6.1 Terra$2 blended · index 77.978% of the #1's index for 13% of its price
  3. Claude Haiku 5.5$0.20 blended · index 59.359% of the #1's index for 1% of its price

The line joins every model that outscores all cheaper ones: along it, no model with a published price scores higher for less. Blended price is 3 input tokens to 1 output, per million. Models without a list price are left off.

what traders pay

polymarket · which company has the best AI model
  1. END NOV$1.4M traded · rules ↗
    81%Google

    Anthropic 21%OpenAI 2%

It settles on the arena.ai Text Arena ↗, as its rules name it, at noon ET on the date. Later dates and every AI release market: AI model odds.

sweeping every 60 seconds

The #1 changes when a new model ships. Know when it does.

Free: an email when a new model takes #1 on the bench index (about once a month so far), plus alerts when a state-of-the-art model launches, about 15 minutes after members hear.

  • Free forever
  • No card
  • Unsubscribe in one click

Want it the minute it answers? Try Signal 7 days free →

Put the answer on your site

A badge that always shows today's #1 (it updates itself hourly) and links here. Paste this where you write about AI models:

Best AI model right now: Claude Fable 5.2, ranked by ArtificialWatch
<a href="https://artificialwatch.com/best-ai-model"><img src="https://artificialwatch.com/badge/top-model.svg" alt="Best AI model right now, ranked by ArtificialWatch" height="46"></a>

Questions

What is the best AI model right now?

Claude Fable 5.2 from Anthropic. It leads ArtificialWatch's combined ranking of 7 public leaderboards and is first on 6 of the 7 on its own. The ranking takes the median of each model's percentile across the boards that score it, so no single board decides it. Next are Gemini 4 Carbon and GPT-6 Astra.

Which AI model is the best for the money?

By the makers' own API prices, blended at 3 input tokens to 1 output: Claude Haiku 5.5 ($0.20 per million, index 59.3), GPT-6.1 Terra ($2 per million, index 77.9) and Gemini 4 Carbon ($4 per million, index 93.7), then Claude Fable 5.2 at $16. No model with a published price scores higher than any of them for less. Gemini 4 Carbon reaches 94% of Claude Fable 5.2's index at 25% of its price.

Which company has the best AI model according to Polymarket?

On Polymarket's "Which company has the best AI model end of November" market, Google is at 81%. That market settles on the arena.ai Text Arena leaderboard, as its rules name it; these are live prices, not a benchmark result.

Which leaderboards is this ranking built from?

LMArena, LiveBench, SimpleBench, LLM Stats, Vals AI, Artificial Analysis and Epoch AI. Their #1 models today: LMArena (Text or WebDev), Claude Fable 5.2; LiveBench, Claude Fable 5.2; SimpleBench, Claude Fable 5.2; LLM Stats, Claude Fable 5.2; Vals AI, Claude Fable 5.2; Artificial Analysis, Gemini 4 Carbon; Epoch AI, Claude Fable 5.2.