Anthropic model product
Claude Mythos is an unreleased general-purpose frontier model from Anthropic, positioned above Opus and not planned for general availability.
Updated Sep 8, 2026. Default version: Claude Mythos Preview
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Claude Mythos Preview.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCharXiv-R | Score93.20% | Rank01 | Participants55 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCyBench | Score100.00% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFigQA | Score89.00% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score92.70% | Rank01 | Participants49 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score87.30% | Rank01 | Participants43 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score59.00% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkUSAMO25 | Score97.60% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score94.60% | Rank02 | Participants247 | Percentile99.59% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score77.80% | Rank02 | Participants55 | Percentile98.15% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score93.90% | Rank02 | Participants113 | Percentile99.11% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score82.00% | Rank02 | Participants51 | Percentile98.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS >128k | Score80.00% | Rank03 | Participants11 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score64.70% | Rank03 | Participants103 | Percentile98.04% | EvidenceC | Evaluated |
| BenchmarkCyberGym | Score83.10% | Rank05 | Participants15 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score86.90% | Rank07 | Participants63 | Percentile90.32% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score79.60% | Rank08 | Participants24 | Percentile69.57% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Claude Mythos Preview. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Mythos Preview | ReleasedN/A | LLMBoard91.30 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Claude Mythos and its available data.
” It is described as a new tier above Opus and is deployed under ASL-3 Standard.
Data as of 2026-09-08.
Common questions about Claude Mythos.
A release date is not available for the default version.
No official standard PAYG price is currently available for Claude Mythos.
Claude Mythos was created by Anthropic.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.