Leaderboard
The top 10 on September 30, 2024
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).
- 1o1-previewClosedOpenAI · released Sep 12, 2024 · 3 weeks oldIntelligence 11.4$29 /M
- 2o1-miniClosedOpenAI · released Sep 12, 2024 · 3 weeks oldIntelligence 9.8No public price
- 3Claude 3 OpusClosedAnthropic · released Mar 4, 2024 · 7 months oldIntelligence 8.7$30 /M
- 4Gemini 1.5 Pro (Sep '24)ClosedGoogle · released Sep 24, 2024 · 6 days oldIntelligence 7.9No public price
- 5GPT-4o (Aug '24)ClosedOpenAI · released Aug 6, 2024 · 8 weeks oldIntelligence 7.7$4.38 /M
- 6Qwen2.5 Instruct 72BOpen weightsAlibaba · released Sep 19, 2024 · 11 days oldIntelligence 7.7$0.48 /M
- 7GPT-4o (May '24)ClosedOpenAI · released May 13, 2024 · 5 months oldIntelligence 7.3$7.50 /M
- 8Llama 3.1 Instruct 405BOpen weightsMeta · released Jul 23, 2024 · 2 months oldIntelligence 7.3No public price
- 9Claude 3.5 Sonnet (June '24)ClosedAnthropic · released Jun 21, 2024 · 3 months oldIntelligence 7.2$6 /M
- 10Gemini 1.5 Flash (Sep '24)ClosedGoogle · released Sep 24, 2024 · 6 days oldIntelligence 7.1No public price
2 years later
What has happened since
430 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 46.2 points higher.
Qwen3.5 4B scores at least as well today for $0.06 per million tokens, against $29 for o1-preview back then.
Grok 3 mini Reasoning matched it for $0.35 per million tokens on Feb 19, 2025.
DeepSeek R1 (Jan '25) from DeepSeek matched it on Jan 20, 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
70 models were out on Sep 30, 2024
Alibaba, scoring 7.7. #6 overall, 3.7 points behind.
Alibaba, scoring 7.7. #6 overall at $0.48, 60× cheaper than #1.
- LFM 40B5.4
- Llama 3.2 Instruct 90B (Vision)6.4
- Llama 3.2 Instruct 3B5.7
- Molmo 7B-D5.6
- Llama 3.2 Instruct 11B (Vision)5.4
- Llama 3.2 Instruct 1B4.8
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.