Leaderboard
The top 10 on May 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).
- 1Claude Opus 4.8ClosedAnthropic · released May 28, 2026 · 3 days oldIntelligence 41.8$10 /M
- 2Claude Opus 4.7ClosedAnthropic · released Apr 16, 2026 · 6 weeks oldIntelligence 40.7$10 /M
- 3GPT-5.4ClosedOpenAI · released Mar 5, 2026 · 3 months oldIntelligence 39$5.62 /M
- 4GPT-5.5ClosedOpenAI · released Apr 23, 2026 · 5 weeks oldIntelligence 38.4$11 /M
- 5Gemini 3.5 FlashClosedGoogle · released May 19, 2026 · 12 days oldIntelligence 33.6$3.38 /M
- 6GPT-5.3 CodexClosedOpenAI · released Feb 5, 2026 · 4 months oldIntelligence 32.5$4.81 /M
- 7Claude Opus 4.6ClosedAnthropic · released Feb 5, 2026 · 4 months oldIntelligence 31.9$10 /M
- 8Muse SparkClosedMeta · released Apr 8, 2026 · 8 weeks oldIntelligence 31.3No public price
- 9GPT-5.2ClosedOpenAI · released Dec 11, 2025 · 6 months oldIntelligence 30.4$4.81 /M
- 10DeepSeek V4 Pro 0424Open weightsDeepSeek · released Apr 24, 2026 · 5 weeks oldIntelligence 30.4$0.54 /M
5 months later
What has happened since
94 models have come out since. Today's best is Claude Opus 5.5 at 57.6, 15.8 points higher.
Claude Haiku 5.5 scores at least as well today for $0.20 per million tokens, against $10 for Claude Opus 4.8 back then.
GLM-5.3-Flash matched it for $0.12 per million tokens on Aug 26, 2026.
Kimi K3 from Kimi matched it on Jul 16, 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
406 models were out on May 31, 2026
DeepSeek, scoring 30.4. #10 overall, 11.4 points behind.
DeepSeek, scoring 30.4. #10 overall at $0.54, 20× cheaper than #1.
- Step 3.7 Flash19.5
- Claude Opus 4.841.8
- LFM2.5-8B-A1B7.2
- HyperNova 60B 260511.7
- MiniCPM5-1B8.8
- Command A+13.1
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.