ModelCompare
Compare

AI model history

What was the top AI model on ?

Claude Fable 5.1 from Anthropic, scoring 53.4 on the Intelligence Index at $20 per million tokens. It came out that very day.

Top Intelligence Index score on each day. Click anywhere to go there.

Leaderboard

The top 10 on September 1, 2026

Ranked by the Artificial Analysis Intelligence Index, with each model's price on that day (per million tokens, 3 parts input to 1 part output).

  1. 1
    Claude Fable 5.1Closed
    Anthropic · released Sep 1, 2026 · out that day
    Intelligence 53.4
    $20 /M
  2. 2
    Claude Opus 5Closed
    Anthropic · released Jul 24, 2026 · 6 weeks old
    Intelligence 50.8
    $10 /M
  3. 3
    Claude Fable 5Closed
    Anthropic · released Jun 9, 2026 · 3 months old
    Intelligence 49.6
    $20 /M
  4. 4
    GPT-5.6 SolClosed
    OpenAI · released Jul 9, 2026 · 8 weeks old
    Intelligence 47
    $8 /M
  5. 5
    GLM-5.3Open weights
    Z.ai · released Aug 18, 2026 · 2 weeks old
    Intelligence 44.8
    $2.15 /M
  6. 6
    Grok 4.6Closed
    xAI · released Aug 12, 2026 · 3 weeks old
    Intelligence 44.3
    $3 /M
  7. 7
    Kimi K3Open weights
    Kimi · released Jul 16, 2026 · 7 weeks old
    Intelligence 43.6
    $6 /M
  8. 8
    GPT-5.6 TerraClosed
    OpenAI · released Jul 9, 2026 · 8 weeks old
    Intelligence 42.1
    $4.50 /M
  9. 9
    Claude Opus 4.8Closed
    Anthropic · released May 28, 2026 · 3 months old
    Intelligence 41.8
    $10 /M
  10. 10
    GLM-5.3-FlashOpen weights
    Z.ai · released Aug 26, 2026 · 6 days old
    Intelligence 41.8
    $0.12 /Mnow $0.24

7 weeks later

What has happened since

#4Where Claude Fable 5.1 ranks today

34 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 4.2 points higher.

5×Cheaper for the same score

Claude Sonnet 5.5 scores at least as well today for $4 per million tokens, against $20 for Claude Fable 5.1 back then.

Not yetUnder $1 per million

No model under $1 per million tokens has matched Claude Fable 5.1's score so far.

Not yetOpen weights

No open-weights model has matched Claude Fable 5.1's score so far.

The race

Which lab held the top spot

OpenAI led for 2.5 years of the 4 years since ChatGPT launched. Anthropic has held #1 since Apr 16, 2026, 6 models in a row. We rank by the Artificial Analysis Intelligence Index. Other leaderboards, such as LMArena's human votes, crown different models.

  • OpenAI65%2.5 years at #1 across 12 models. Longest: GPT-4, 8 months.
  • Anthropic33%15 months at #1 across 11 models. Longest: Claude 3 Opus, 6 months.
  • xAI2%4 weeks at #1 across 1 model. Longest: Grok 4, 4 weeks.
  • Google<1%6 days at #1 across 1 model. Longest: Gemini 3 Pro Preview, 6 days.

The wider field

466 models were out on Sep 1, 2026

Best open model
GLM-5.3

Z.ai, scoring 44.8. #5 overall, 8.6 points behind.

Best under $1 per million
GLM-5.3-Flash

Z.ai, scoring 41.8. #10 overall at $0.12, 170× cheaper than #1.

New in the 30 days before · 29
  • Claude Fable 5.153.4
  • Apodex 1.126.4
  • GLM-5.3-Flash41.8
  • Qwen3.8-Flash-Next39.8
  • Agnes 2.5 Pro Beta35.2
  • Granite 4.2 30B12.7
and 23 more

Browse

The top AI model, month by month

2026
2025
2024
2023
2022

Try today's top models on your own prompt

Scores tell you who leads on average. Send one prompt to up to six models and see which answer you'd actually use, with what each one cost. For the long view of prices, read Six months later, the best AI costs 20× less.

Compare models

Scores and release dates from Artificial Analysis (Intelligence Index, best published effort of each model), data through October 18, 2026. Prices are list prices on the day, including later cuts we know of. Models without a public price are ranked but not priced.