Leaderboard
The top 10 on August 5, 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).
- 1Claude 4.1 OpusClosedAnthropic · released Aug 5, 2025 · out that dayIntelligence 22.8$30 /M
- 2Grok 4ClosedxAI · released Jul 10, 2025 · 4 weeks oldIntelligence 22.5$6 /M
- 3o3-proClosedOpenAI · released Jun 10, 2025 · 8 weeks oldIntelligence 21.9$35 /M
- 4Claude 4 OpusClosedAnthropic · released May 22, 2025 · 2 months oldIntelligence 20.6$30 /M
- 5o3ClosedOpenAI · released Apr 16, 2025 · 4 months oldIntelligence 20.2$3.50 /M
- 6Claude 4 SonnetClosedAnthropic · released May 22, 2025 · 2 months oldIntelligence 18.9$6 /M
- 7Claude 3.7 SonnetClosedAnthropic · released Feb 24, 2025 · 5 months oldIntelligence 17.7$6 /M
- 8o4-miniClosedOpenAI · released Apr 16, 2025 · 4 months oldIntelligence 16.7$1.93 /M
- 9Gemini 2.5 ProClosedGoogle · released Jun 5, 2025 · 2 months oldIntelligence 16.1$3.44 /M
- 10o1ClosedOpenAI · released Dec 5, 2024 · 8 months oldIntelligence 15.2$26 /M
14 months later
What has happened since
297 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 34.8 points higher.
DeepSeek V4 Flash 0420 scores at least as well today for $0.14 per million tokens, against $30 for Claude 4.1 Opus back then.
MiniMax-M2.5 matched it for $0.53 per million tokens on Feb 12, 2026.
Kimi K2.5 from Kimi matched it on Jan 27, 2026, 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
203 models were out on Aug 5, 2025
DeepSeek, scoring 13.1. #15 overall, 9.7 points behind.
xAI, scoring 14.6. #12 overall at $0.35, 85× cheaper than #1.
- Claude 4.1 Opus22.8
- gpt-oss-120b11.6
- gpt-oss-20b10
- Qwen3 Coder 30B A3B Instruct9.6
- Qwen3 30B A3B 25079.8
- Qwen3 30B A3B 2507 Instruct7.5
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.