🏆 Most Intelligent AI Models

Ranking of language models by overall intelligence. These are the most capable AI models available today.Updated August 2026. Based on independent benchmark data.

Why This Matters

Choosing the right model for most intelligent ai models is about more than raw benchmark scores. The models below are ranked using a weighted blend of category-specific benchmarks, arena Elo, and the intelligence index — but real-world performance depends on your context window, latency budget, and integration path.

For most intelligent ai models, we weighted the benchmarks that most strongly predict success in production: task accuracy first, then speed and cost efficiency. Leaders on this page consistently outperform on both standardized tests and real-world workloads.

If you operate under a strict budget, check the Best Value LLMs ranking. If latency matters more than raw quality, see Fastest LLMs. Both pages use the same underlying dataset with different weightings.

#ModelProviderScoreSpeedPrice (output)
1Claude Mythos PreviewAnthropic97.480 t/s$15/M
2Claude Mythos 5Anthropic79.050 t/s$50/M
3Claude Opus 4 6 ThinkingAnthropic75.050 t/s$15/M
4Claude Opus 4 7 ThinkingAnthropic75.050 t/s$15/M
5Claude Opus 5 MaxAnthropic75.050 t/s$15/M
6Gemini 3.1 Pro PreviewGoogle74.050 t/s$5/M
7Kimi K3 MaxMoonshot AI74.050 t/s$3/M
8Claude Opus 4 8 ThinkingAnthropic74.050 t/s$15/M
9GPT 5.6 Sol XhighOpenAI74.050 t/s$10/M
10GPT 5.5 HighOpenAI74.050 t/s$10/M
11GPT 5.4 HighOpenAI74.050 t/s$10/M
12Gemini 3.5 Flash HighGoogle74.050 t/s$5/M
13GPT 5.2 Chat Latest 20260210OpenAI74.050 t/s$10/M
14Qwen3.7 Max PreviewAlibaba74.050 t/s$2/M
15Grok 4.20 Beta1xAI74.050 t/s$15/M
16Gemini 3.5 Flash MediumGoogle74.050 t/s$5/M
17GPT 5.5 InstantOpenAI74.050 t/s$10/M
18Claude Opus 4 5 20251101 Thinking 32kAnthropic74.050 t/s$15/M
19Grok 4.20 Beta 0309 ReasoningxAI74.050 t/s$15/M
20Grok 4.20 Multi Agent Beta 0309xAI74.050 t/s$15/M

Methodology

Rankings are based on independent benchmark evaluations. The most intelligent ai models score is computed from multiple standardized benchmarks and normalized to 0–100. Data is updated regularly from public benchmark results.

Related Rankings

💻 Coding🧠 Reasoning📚 Knowledge👁️ Vision💰 Best Value AI Models⚡ Fastest AI Models