Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
Meta AI models by SI-IQ
Meta AI has 16 models with independent benchmark results in our data. The best ranked is Muse Spark Open with an SI-IQ of 127.
Models
| 1 | Muse Spark Openopen Meta AI | 127124–130 | 7 |
| 2 | Llama 4 Maverickopen Meta AI | 8177–85 | 7 |
| 3 | Llama 3.3 70Bopen Meta AI | 6661–71 | 6 |
| 4 | Muse Wonder Meta AI | 136133–139 | 4 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 5 | Muse Spark 1.3 Meta AI | 128125–131 | 5 results in fewer than 3 areas; results from fewer than 2 evaluators |
| 6 | Muse Spark 1.1 Meta AI | 125116–133 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 7 | Muse Spark 1.2 Meta AI | 121112–129 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 8 | Muse Spark Meta AI | 118110–126 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 9 | Llama 4 Scoutopen Meta AI | 7368–78 | 4 results from fewer than 5 benchmarks |
| 10 | Llama 3.1-405Bopen Meta AI | 7065–75 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 11 | Llama 3.1-70Bopen Meta AI | 6358–68 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 12 | Llama 3.2 3Bopen Meta AI | 6142–80 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas |
| 13 | Llama 3-70Bopen Meta AI | 5752–62 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 14 | Llama 3.1-8Bopen Meta AI | 5549–60 | 4 results from fewer than 5 benchmarks; results in fewer than 3 areas |
| 15 | Llama 3.2 1Bopen Meta AI | 4227–58 | 3 results from fewer than 5 benchmarks |
| 16 | Llama 3-8Bopen Meta AI | 4034–46 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).