Skip to main content
ModelScale

Claude Mythos Preview

Anthropic · Proprietary · bench-align-v5

Canonical idclaude-mythos-preview
Overall scoreUnavailable
Context windowUnavailable
Release date2026-04-07
Access typeProprietary
Blended $/1M$50.0075% input / 25% output

Capability shape

Seven axes from the ranking source. A missing axis is drawn as a gap.

Capability evidence

AgenticUnavailable
CodingUnavailable
KnowledgeUnavailable
ReasoningUnavailable
Multimodal & GroundedUnavailable
Instruction FollowingUnavailable
MathUnavailable

Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.

Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.

Evidence key: Unavailable

Runtime measurements
MeasurementValueObservedLast goodEvidence
Time to first tokenUnavailableUnavailableUnavailable
ThroughputUnavailableUnavailableUnavailable

Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.

Endpoint and price matrix

Every published price component, including cache reads and writes.

Price components
ComponentUSDEvidence
Input / 1M tokens$25.00
Output / 1M tokens$125.00
Cache read / 1M tokensUnavailable
Cache write / 1M tokensUnavailable
Blended / 1M (75% input / 25% output)$50.00
Self-hosted listingAnthropic's April 7, 2026 Project Glasswing announcement states that usage credits covered the research preview and that participating organizations could later access Claude Mythos Preview at $25 input / $125 output per million tokens. The model was never generally available and was replaced by Claude Mythos 5.The rates above are a hosted price matched from another provider, not a first-party list price.

Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.

Modelled monthly cost$140.80
Modelled tokens2.82M
Open the simulatorChange this workload

Benchmark record

5 matched benchmark rows with their published value, unit, and provenance.

Agentic

Agentic benchmarks
BenchmarkValueTasksDifficultyProvenance
CyberGym
CyberGym
83.11,507 vulnerability analysis instancesReal-world cybersecurityCyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
ExploitGym
ExploitGym
17.5898 exploitation tasksAdvanced cybersecurity exploitationExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

external

external benchmarks
BenchmarkValueTasksDifficultyProvenance
ExploitBench
ExploitBench v8-bench
69V8 exploit synthesis runsBrowser exploitation and cybersecurityExploitBench
SCONE post-cutoff success
SCONE Post-Cutoff Exploit Success
10012 post-cutoff smart-contract vulnerabilitiesSmart-contract exploitationEvaluating frontier models on software exploitation
SCONE simulated revenue
SCONE Post-Cutoff Simulated Exploit Revenue
3512 post-cutoff smart-contract vulnerabilitiesSmart-contract exploitationEvaluating frontier models on software exploitation

Lifecycle and limitations log

Lifecycle events the source associates with this model, plus what this profile does not claim.

No lifecycle event references this model.

That is not evidence the model has no lifecycle plan — only that this source published none.

What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.