Leaderboard
The top 10 on June 10, 2025
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).
- 1o3-proClosedOpenAI · released Jun 10, 2025 · out that dayIntelligence 21.9$35 /M
- 2Claude 4 OpusClosedAnthropic · released May 22, 2025 · 3 weeks oldIntelligence 20.6$30 /M
- 3o3ClosedOpenAI · released Apr 16, 2025 · 8 weeks oldIntelligence 20.2$3.50 /M
- 4Claude 4 SonnetClosedAnthropic · released May 22, 2025 · 3 weeks oldIntelligence 18.9$6 /M
- 5Claude 3.7 SonnetClosedAnthropic · released Feb 24, 2025 · 3 months oldIntelligence 17.7$6 /M
- 6o4-miniClosedOpenAI · released Apr 16, 2025 · 8 weeks oldIntelligence 16.7$1.93 /M
- 7Gemini 2.5 ProClosedGoogle · released Jun 5, 2025 · 5 days oldIntelligence 16.1$3.44 /M
- 8o1ClosedOpenAI · released Dec 5, 2024 · 6 months oldIntelligence 15.2$26 /M
- 9Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · released Mar 25, 2025 · 3 months oldIntelligence 15No public price
- 10Grok 3 mini ReasoningClosedxAI · released Feb 19, 2025 · 4 months oldIntelligence 14.6$0.35 /M
16 months later
What has happened since
326 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 35.7 points higher.
Hy3-preview scores at least as well today for $0.10 per million tokens, against $35 for o3-pro back then.
MiniMax-M2.5 matched it for $0.53 per million tokens on Feb 12, 2026.
Kimi K2 Thinking from Kimi matched it on Nov 6, 2025, free to download and run.
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
174 models were out on Jun 10, 2025
DeepSeek, scoring 13.1. #13 overall, 8.8 points behind.
xAI, scoring 14.6. #10 overall at $0.35, 100× cheaper than #1.
- o3-pro21.9
- Magistral Medium 19.1
- Magistral Small 18.2
- Gemini 2.5 Pro16.1
- DeepSeek R1 0528 Qwen3 8B8.1
- DeepSeek R1 0528 (May '25)13.1
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.