Models
Every model our stories named. Each number links to its story and source. A dot means not checked yet.
| Model | Maker | Latest | Per million tokens, in / out | Context | Maker's own benchmarks | Measured by others |
|---|---|---|---|---|---|---|
| Muse | Meta | 30 Oct | not checked yet | not checked yet | not checked yet | not checked yet |
| muse-spark-open | Meta | 16 Oct | not checked yet | 1,000,000 tokens | MCP-Atlas (Meta's model card, xhigh) 89.2% · Terminal-Bench 2.1 (Meta's model card, xhigh) 76.4% · Artificial Analysis Intelligence Index (Meta's model card, xhigh) 39% | not checked yet |
| Muse Wonder | Meta | 13 Oct | not checked yet | not checked yet | not checked yet | not checked yet |
| Muse Spark 1.3 | Meta | not checked yet | not checked yet | not checked yet | CheatBench cheating rate with Muse Code (lower is better) 39% |
Maker's own: what a company measured on its own model, from its model card, system card or announcement. A claim about its own product, and labelled so.
Measured by others: a safety institute, a research group or a public benchmark run by someone other than the maker.
Prices for prompts over 100,000 tokens where a model has two tiers. Benchmarks come from each release's own documents, collected by the registrar.