Anthropic
Claude Mythos 5 was distinguished by a separate access rule for the model core it shared with Claude Fable 5. It followed Claude Mythos Preview, preceded Claude Mythos 5.1, and remained a program for vetted Glasswing partners rather than an API tier anyone could buy.
Anthropic launched Mythos 5 on June 9 and suspended access on June 12. Fable returned globally on July 1. In its detailed June 30 notice, Anthropic said Mythos 5 access had already been restored for a set of US organizations, while broader access for Glasswing partners was still being expanded. The difference in availability remained part of the safety program.
| Specification | Value and source |
|---|---|
| Weights | ProprietarySource |
| Access | APISource |
| Context window | 1,000,000 tokensSource |
| Knowledge cutoff | January 2026Source |
| Notes | Shares Fable 5's specs and pricing, without the safety classifiers. Invitation-only limited availability via Project Glasswing for vetted cybersecurity/biomedical/infrastructure partners, no self-serve signup. Briefly suspended 2026-06-12 to 2026-06-30 under the same export control directive as Fable 5; access restored 2026-07-01.Source |
| API model ID | claude-mythos-5Source |
| Source status | active (invite only)Source |
| Release | 2026-06-09Source |
| Maximum output | 128,000 tokensSource |
| Input | Text, imagesSource |
| Output | TextSource |
| Reasoning mode | adaptive (always on); default highSource |
| Knowledge cutoff | 2026-01Source |
| Tool calling | YesSource |
| Structured output | YesSource |
Overall
1,266 hard-to-find research tasks with short, unambiguous answers. The benchmark rewards persistent fact finding and only partly represents open-ended research reports or typical user questions.
Note (Claude Mythos 5): Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
higher is betterAs of September 2, 2026Scale: 0% - 100%
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Each test shows the latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.
A community classic for free-form SVG drawing.
Claude Mythos 5
No available test access
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)25.6 / 100
| Type | Evidence and data date |
|---|---|
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 7, 2026. |
| Output | Documented modalities. Retrieved September 7, 2026. |
| Research status | Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | parameters-billions Original wording Anthropic does not publish parameter counts for this model. |
| Not found in the inspected sources | active-parameters-billions Original wording Anthropic does not publish active parameter counts for this model. |
| Unresolved | profile-benchmarks-identity Original wording The public table combines the same underlying Mythos 5/Fable 5 model and reports the higher score where safeguards differ; it does not expose separate exact per-variant cells. |
| Unresolved | profile-benchmarks Original wording Official launch table combines Mythos 5 / Fable 5 and reports the higher variant score; retained as separate context, not an exact per-profile benchmark. |
| Additional source | Model metadata · Anthropic, Claude Fable 5 and Claude Mythos 5 · Editorial description reviewed October 2, 2026 |
| Additional source | Context window data |
| Additional source | Knowledge cutoff data |
| Additional source | OpenAI (retrieved September 2, 2026) |
| Additional source | Anthropic, Redeploying Fable 5 · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |
| Additional source | Anthropic "Migrating to Claude Mythos 5 and Claude Fable 5" guide (2026-09-19) |
| Additional source | Anthropic "Migrating to Claude Fable 5.1 and Claude Mythos 5.1" guide (2026-09-19) |
