Leaderboard
The top 10 on November 30, 2023
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). The index uses today's harder tests, so models from before late 2024 all score between 5 and 9 and their order is rough.
- 1GPT-4 TurboClosedOpenAI · released Nov 6, 2023 · 3 weeks oldIntelligence 7$15 /M
- 2GPT-4ClosedOpenAI · released Mar 14, 2023 · 9 months oldIntelligence 6.7$38 /M
- 3Llama 2 Chat 7BOpen weightsMeta · released Jul 18, 2023 · 4 months oldIntelligence 5.7$0.10 /M
- 4Claude 2.1ClosedAnthropic · released Nov 21, 2023 · 9 days oldIntelligence 5.6No public price
- 5GPT-3.5 TurboClosedOpenAI · released Nov 30, 2022 · 12 months oldIntelligence 5.5$0.75 /M
- 6Claude 2.0ClosedAnthropic · released Jul 11, 2023 · 5 months oldIntelligence 5.5No public price
- 7PALM-2ClosedGoogle · released May 10, 2023 · 7 months oldIntelligence 5.4No public price
- 8Qwen Chat 72BOpen weightsAlibaba · released Nov 30, 2023 · out that dayIntelligence 5.4No public price
- 9Llama 2 Chat 13BOpen weightsMeta · released Jul 18, 2023 · 4 months oldIntelligence 5.3No public price
- 10Llama 2 Chat 70BOpen weightsMeta · released Jul 18, 2023 · 4 months oldIntelligence 5.3No public price
3 years later
What has happened since
485 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 50.6 points higher.
Gemma 4 E4B scores at least as well today for $0.04 per million tokens, against $15 for GPT-4 Turbo back then.
Qwen2.5 Instruct 72B matched it for $0.48 per million tokens on Sep 19, 2024.
Llama 3.1 Instruct 405B from Meta matched it on Jul 23, 2024, 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
15 models were out on Nov 30, 2023
Meta, scoring 5.7. #3 overall, 1.3 points behind.
Meta, scoring 5.7. #3 overall at $0.10, 150× cheaper than #1.
- Qwen Chat 72B5.4
- DeepSeek LLM 67B Chat (V1)5.3
- Claude 2.15.6
- GPT-4 Turbo7
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.