Model tiers by benchmark average
A breakdown of the index by model category, with model counts, median input price and average benchmark score.
What the data shows
The largest category is multimodal with 215 models. Category averages differ, but the spread inside each category is often larger than the difference between categories.
Categories are a coarse filter. Use them to narrow the index, then compare individual models on the benchmarks that matter.
How to read it
- Do not treat category averages as rankings.
- Check the price distribution inside a category.
- Compare the best model in each category.
- Use tags for finer filtering.
Model tiers
| Category | Models | Median input | Avg score |
|---|---|---|---|
| multimodal | 215 | $5.05 | 77.6 |
| small open-weight | 153 | $0.87 | 53.5 |
| open-weight | 74 | $2.71 | 68.2 |
| frontier | 72 | $18.09 | 85.8 |
| mid-range | 72 | $7.35 | 67.5 |
| coding | 14 | $3.76 | 68.6 |
Methodology
This story uses the AI & LLM Index dataset: 600 models, 40 providers and 12 benchmarks. Prices are listed per million tokens. Scores are modelled estimates on a 0–100 scale and are not official benchmark results. Figures are rounded for readability.
Related
FAQ
What does the Model tiers by benchmark average data show?
A breakdown of the index by model category, with model counts, median input price and average benchmark score.
Are the numbers official?
No. Prices and scores are compiled for this demo index. Benchmark values are modelled estimates, not official results. Verify figures with the provider or benchmark owner before making decisions.
How should I use this ranking?
Use it to form a shortlist. Check the specific model pages, compare price and context, and test the shortlist on your own examples before committing.