AI benchmark results and model performance
Individual benchmark scores plotted by date.
| Organisation | Model | Reported | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|---|
| Claude Fable 5 | 09 Jun 2026 | 11.50% | Low effort; mirrored from Anthropic's Mythos-class FrontierCode compute-scaling chart because Fable 5 and Mythos 5 are the same underlying model | Yes | Source | |
| Claude Mythos 5 | 09 Jun 2026 | 11.50% | Low effort; Anthropic Mythos-class FrontierCode compute-scaling chart | Yes | Source | |
| Claude Sonnet 5 | 30 Jun 2026 | 38.80% | FrontierCode v1; adaptive thinking at max effort; summary-table score | Yes | Source |
