Leaderboard
The top 10 on July 24, 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).
- 1Claude Opus 5ClosedAnthropic · released Jul 24, 2026 · out that dayIntelligence 50.8$10 /M
- 2Claude Fable 5ClosedAnthropic · released Jun 9, 2026 · 6 weeks oldIntelligence 49.6$20 /M
- 3GPT-5.6 SolClosedOpenAI · released Jul 9, 2026 · 2 weeks oldIntelligence 47$11 /Mnow $8
- 4Kimi K3Open weightsKimi · released Jul 16, 2026 · 8 days oldIntelligence 43.6$6 /M
- 5GPT-5.6 TerraClosedOpenAI · released Jul 9, 2026 · 2 weeks oldIntelligence 42.1$5.63 /Mnow $4.50
- 6Claude Opus 4.8ClosedAnthropic · released May 28, 2026 · 8 weeks oldIntelligence 41.8$10 /M
- 7Claude Opus 4.7ClosedAnthropic · released Apr 16, 2026 · 3 months oldIntelligence 40.7$10 /M
- 8GPT-5.4ClosedOpenAI · released Mar 5, 2026 · 5 months oldIntelligence 39$5.62 /M
- 9Grok 4.5ClosedxAI · released Jul 8, 2026 · 2 weeks oldIntelligence 38.8$3 /M
- 10GPT-5.5ClosedOpenAI · released Apr 23, 2026 · 3 months oldIntelligence 38.4$11 /M
3 months later
What has happened since
65 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 6.8 points higher.
Claude Sonnet 5.5 scores at least as well today for $4 per million tokens, against $10 for Claude Opus 5 back then.
No model under $1 per million tokens has matched Claude Opus 5's score so far.
No open-weights model has matched Claude Opus 5'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.
The wider field
435 models were out on Jul 24, 2026
Kimi, scoring 43.6. #4 overall, 7.2 points behind.
DeepSeek, scoring 30.4. #23 overall at $0.54, 20× cheaper than #1.
- Claude Opus 550.8
- Celeris-16.3
- G9v3-3B10.8
- Gemini 3.6 Flash34
- Gemini 3.5 Flash-Lite22.2
- Kimi K343.6
Browse
The top AI model, month by month
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.
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.