# Claude Mythos 5

Anthropic · Proprietary · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/claude-mythos-5  
JSON: https://modelscale.dev/api/model/claude-mythos-5

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `claude-mythos-5` | — |
| Overall score | Unavailable | Unavailable · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 84 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2026-06-09 | Observed 2026-11-21 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $20.00 | Derived from the input and output rates below |

**Only a verified score is published.** BenchLM publishes no overall score for this model, so the overall score stays unavailable. The verified score beside it is a separate figure in BenchLM's data. BenchLM does not document how the two are calculated differently, and they can differ widely, so one is never used in place of the other.

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | 84.1 | Observed 2026-11-21 · source benchlm:models | 81.5 | Observed 2026-11-21 · source benchlm:models |
| Coding | 87.3 | Observed 2026-11-21 · source benchlm:models | 87.2 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 91.3 | Observed 2026-11-21 · source benchlm:models | 91.2 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Multimodal & Grounded | 90.4 | Observed 2026-11-21 · source benchlm:models | 90.4 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $10.00 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $50.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $1.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $20.00 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Pricing note.** Anthropic's June 9, 2026 Claude Fable 5 and Claude Mythos 5 launch says both models are offered at $10 input / $50 output per million tokens. Mythos 5 is restricted to Glasswing partners and trusted access programs.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $56.32 |
| Modelled tokens | 2.82M |

## Benchmark record

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 94.1 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| HLE (Humanity's Last Exam) | 64.5 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| HLE w/o tools (Humanity's Last Exam without tools) | 59 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 88.0 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| Terminal-Bench 2.0 | 88.0 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 95.5 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| SWE-bench Pro | 80.3 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| USAMO 2026 (United States of America Mathematical Olympiad 2026) | 97.6 | 6 proof-based problems | International olympiad level | [United States of America Mathematical Olympiad](https://www.maa.org/math-competitions/usamo) |

### Multilingual

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SWE Multilingual (SWE-bench Multilingual) | 92.2 | 300 problems across 9 languages | Professional multilingual software engineering | [SWE-bench Multilingual](https://www.swebench.com/multilingual) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.0 | 88 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Terminal-Bench 2.1 | 88.0 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 88 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| OSWorld-Verified | 85 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | [OSWorld](https://os-world.github.io/) |
| CyberGym | 83.8 | 1,507 vulnerability analysis instances | Real-world cybersecurity | [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://www.cybergym.io/) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| CharXiv (CharXiv Reasoning) | 93.5 | Scientific chart reasoning | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |
| CharXiv w/o tools (CharXiv Reasoning without tools) | 88.9 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://charxiv.github.io/) |
| SWE-bench Multimodal | 54.9 | Multimodal software engineering tasks | Frontier multimodal coding | [SWE-bench Multimodal](https://www.swebench.com/multimodal) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ExploitBench (ExploitBench v8-bench) | 78 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | [ExploitBench](https://exploitbench.ai/) |
| The Last Ones completion (The Last Ones Cyber Range Completion Rate) | 60 | 10 long-horizon runs | Long-horizon cyber operations | [UK AISI and CAISI Preliminary Assessment of Kimi K3's Cyber Capabilities](https://www.nist.gov/news-events/news/2026/07/uk-aisi-caisi-preliminary-assessment-kimi-k3s-cyber-capabilities) |
| Firefox 147 exploits (Firefox 147 Working Exploit Rate) | 88.4 | 250 Firefox 147 vulnerability trials | Browser exploit development | [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5) |
| Anthropic OSS-Fuzz crash (Anthropic OSS-Fuzz Any-Crash Rate) | 80.0 | Approximately 830 OSS-Fuzz entry points | Vulnerability discovery | [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5) |
| Anthropic OSS-Fuzz write primitive (Anthropic OSS-Fuzz Write-Primitive-or-Higher Rate) | 32.4 | Approximately 830 OSS-Fuzz entry points | Vulnerability exploitation | [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

| Event | Type | Confirmation | Announced | Effective | Replacement | Source |
| --- | --- | --- | --- | --- | --- | --- |
| Claude Fable 5 and Claude Mythos 5 | Release | confirmed | Unavailable | 2026-06-09 | — | [Anthropic](https://www.anthropic.com/news/claude-fable-5-mythos-5) |

## What this profile does not claim

Values 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. Last attempted fetch for this model's score: 2026-11-21 01:17 UTC.
