Claude Mythos Preview released
Anthropic · Model release
Source confirmed
Data as of October 5, 2026 · How the score is built
EstablishedProprietaryReasoning
Claude Mythos Preview
Decision readingClaude Mythos Preview is tracked, but not publicly ranked yet. The profile exposes 5 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Apr 7, 2026 — see all recent releases
Claude Mythos Preview will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 51Not eligible for a public rank
Price
$25input / $125 output
input median $0.95blended $75
Speed
Not measured
field median 90 tok/sTime to first token not measured
Context
Not published
field median 256,000No exact-model context limit is sourced
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
5 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 5 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%2 benchmarksVerified | Score pending | 2 benchmarks | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
5 of 649 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic2/2 verified
- CodingNot measured
- ReasoningNot measured
- MultimodalNot measured
- KnowledgeNot measured
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Verified sourceProvisionalNot measured
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| CyberGym | Score83.1% | Versus best verified row Best verified: MiMo-V2.6-Flash · 95.1% | Gap12 behind | WeightDisplay only | Benchmark exact |
| ExploitGym | Score17.5% | Versus best verified row Best verified: GPT-6 Astra · 42.4% | Gap24.9 behind | WeightDisplay only | Benchmark exact |
External signals3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ExploitBenchExploitBench v8-bench | Score69% | Versus best verified row Best verified: GPT-6 Astra · 100% | Gap31 behind | WeightDisplay only | |
| SCONE post-cutoff successSCONE Post-Cutoff Exploit Success | Score100% | Versus best verified row Best verified: Claude Mythos Preview · 100% | GapBest verified | WeightDisplay only | |
| SCONE simulated revenueSCONE Post-Cutoff Simulated Exploit Revenue | Score35% | Versus best verified row Best verified: Claude Mythos Preview · 35% | GapBest verified | WeightDisplay only |
Bars run 0–100; the dark tick marks the best source-verified value
All 5 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyClaude Mythos Preview release history
Radar confirmed these at the source. Use Claude Mythos Preview in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- claude-mythos-previewAnthropic Project Glasswing
- Context window
- Not publishedAnthropic Project Glasswing
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yetAnthropic Project Glasswing
- Output modalities
- Not sourced yetAnthropic Project Glasswing
- Parameters
- Not disclosed by the provider
- Availability
- Project Glasswing participantsAnthropic Project Glasswing
- Cloud regions
- Not tracked yet
- Lifecycle
- limited accessAnthropic Project Glasswing
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordAnthropic Project Glasswing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Claude Mythos Preview, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Claude Mythos Preview is a proprietary model. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Anthropic released Claude Mythos Preview only to Project Glasswing partners. Anthropic later replaced it with Claude Mythos 5; it was never generally available.
Historical, display-only cyber profile for Anthropic's April 7, 2026 Claude Mythos Preview. The CyberGym row comes from the Project Glasswing launch, ExploitGym and ExploitBench come from Anthropic's exploit-evaluation report, and SCONE uses the report's 12-task post-cutoff set. These results belong to Mythos Preview and are kept separate from Claude Mythos 5 and the safeguarded Claude Fable 5 release.
Claude Mythos Preview sits in the Claude Mythos family with Claude Mythos 5, Claude Mythos 5.1. 5 of 649 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 5, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Claude Mythos Preview perform overall in AI benchmarks?
Claude Mythos Preview has 5 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Claude Mythos Preview good for agentic tool use and computer tasks?
Claude Mythos Preview has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Which sibling models are related to Claude Mythos Preview?
Claude Mythos Preview belongs to the Claude Mythos family. Related tracked variants include Claude Mythos 5, Claude Mythos 5.1. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Claude Mythos Preview have full benchmark coverage on BenchLM?
No. Claude Mythos Preview currently has 5 source-displayable rows across 649 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Claude Mythos Preview?
Claude Mythos Preview's provider has not published a context-window limit for this exact model. The profile leaves the value unavailable instead of borrowing a number from an earlier family member or a third-party route. Maximum output length is tracked separately when the provider documents it.