Leaderboard
The top 10 on January 31, 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).
- 1o1ClosedOpenAI · released Dec 5, 2024 · 8 weeks oldIntelligence 15.2$26 /M
- 2o3-miniClosedOpenAI · released Jan 31, 2025 · out that dayIntelligence 12.5$1.93 /M
- 3Sonar Reasoning ProClosedPerplexity · released Jan 28, 2025 · 3 days oldIntelligence 11.8No public price
- 4o1-previewClosedOpenAI · released Sep 12, 2024 · 5 months oldIntelligence 11.4$29 /M
- 5DeepSeek R1 (Jan '25)Open weightsDeepSeek · released Jan 20, 2025 · 11 days oldIntelligence 11.4$2.50 /M
- 6o1-miniClosedOpenAI · released Sep 12, 2024 · 5 months oldIntelligence 9.8No public price
- 7Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · released Jan 21, 2025 · 10 days oldIntelligence 9.4No public price
- 8Claude 3.5 HaikuClosedAnthropic · released Oct 22, 2024 · 3 months oldIntelligence 8.9No public price
- 9Claude 3 OpusClosedAnthropic · released Mar 4, 2024 · 11 months oldIntelligence 8.7$30 /M
- 10Sonar ReasoningClosedPerplexity · released Jan 28, 2025 · 3 days oldIntelligence 8.7No public price
1.5 years later
What has happened since
392 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 42.4 points higher.
Hy3-preview scores at least as well today for $0.10 per million tokens, against $26 for o1 back then.
GPT-5 mini matched it for $0.69 per million tokens on Aug 7, 2025.
Kimi K2 0905 from Kimi matched it on Sep 5, 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
108 models were out on Jan 31, 2025
DeepSeek, scoring 11.4. #5 overall, 3.8 points behind.
DeepSeek, scoring 8.5. #11 overall at $0.46, 55× cheaper than #1.
- o3-mini12.5
- Llama 3.1 Tulu3 405B7.2
- Mistral Small 36.7
- Sonar Reasoning Pro11.8
- Sonar Reasoning8.7
- Qwen2.5 Max8
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.