AI - Paski.devClaude Mythos 5
Anthropic llmLimited-availability counterpart to Claude Fable 5, sharing the same underlying model with some safeguards lifted for approved cyber-defence and life-sciences customers.
overall ⌄
83.7
1 of 93 ranked
price · $/M tokens
10 / 50
in / out, as of 2026-07-25
to run it yourself ⌄
API only
no weights to run
Benchmarks
What its maker published, and what anyone else measured. Every figure links the document it came from.
| benchmark | published | measured |
|---|---|---|
| GPQA | 94.1 | — |
| SWE-bench | 95.5 thinking | — |
| SWE-bench Pro | 80.3 thinking | — |
| HLE | 59 auto | — |
| BrowseComp | 88 max | — |
Cheaper, and at least as good
Nothing is both cheaper and ranked as high. This model is on the value frontier — whatever you pay for it, you are paying for something.
Lineage
↑ base Claude Fable 5
Metadata
| org | Anthropic |
| released | 2026-06-09 |
| license | proprietary |