Leaderboard
The top 10 on January 31, 2026
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).
- 1GPT-5.2ClosedOpenAI · released Dec 11, 2025 · 7 weeks oldIntelligence 30.4$4.81 /M
- 2Claude Opus 4.5ClosedAnthropic · released Nov 24, 2025 · 2 months oldIntelligence 29.1$10 /M
- 3GPT-5.2 CodexClosedOpenAI · released Dec 11, 2025 · 7 weeks oldIntelligence 28.5$4.81 /M
- 4Gemini 3 Pro PreviewClosedGoogle · released Nov 18, 2025 · 2 months oldIntelligence 28$4.50 /M
- 5Gemini 3 Flash PreviewClosedGoogle · released Dec 17, 2025 · 6 weeks oldIntelligence 26.3$1.12 /M
- 6GPT-5 CodexClosedOpenAI · released Sep 23, 2025 · 4 months oldIntelligence 24.9$3.44 /M
- 7GPT-5.1ClosedOpenAI · released Nov 13, 2025 · 3 months oldIntelligence 24.7$3.44 /M
- 8GPT-5.1 CodexClosedOpenAI · released Nov 13, 2025 · 3 months oldIntelligence 23.7$3.44 /M
- 9Kimi K2.5Open weightsKimi · released Jan 27, 2026 · 4 days oldIntelligence 23.5$1.14 /M
- 10GPT-5ClosedOpenAI · released Aug 7, 2025 · 6 months oldIntelligence 23$3.44 /M
9 months later
What has happened since
180 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 27.2 points higher.
Agnes 2.5 Pro Beta scores at least as well today for $0.15 per million tokens, against $4.81 for GPT-5.2 back then.
DeepSeek V4 Pro 0424 matched it for $0.54 per million tokens on May 22, 2026.
DeepSeek V4 Pro 0424 from DeepSeek matched it on Apr 24, 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
320 models were out on Jan 31, 2026
Kimi, scoring 23.5. #9 overall, 6.9 points behind.
DeepSeek, scoring 21.5. #16 overall at $0.32, 15× cheaper than #1.
- LongCat Flash Lite11.5
- Kimi K2.523.5
- Qwen3 Max Thinking21.3
- Step3 VL 10B7.7
- LFM2.5-1.2B-Thinking5.2
- GLM-4.7-Flash14.9
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.