# Claude Fable 5.1

Anthropic · Proprietary · rank 12 · 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-fable-5-1  
JSON: https://modelscale.dev/api/model/claude-fable-5-1

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `claude-fable-5-1` | — |
| Overall score | 78.6 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 78 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-11-21 · source benchlm:models |
| Max output (models.dev) | 128,000 tokens | Observed 2026-11-21 · source modelsdev:catalog |
| Modalities (models.dev) | Input: text, image, PDF · Output: text | Observed 2026-11-21 · source modelsdev:catalog |
| Release date | 2026-09-01 | 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 |

## 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 | 60.7 | Observed 2026-11-21 · source benchlm:models | 46.6 | Observed 2026-11-21 · source benchlm:models |
| Coding | 90.8 | Observed 2026-11-21 · source benchlm:models | 90.8 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 95.2 | Observed 2026-11-21 · source benchlm:models | 95.2 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 82.3 | Observed 2026-11-21 · source benchlm:models | 82.3 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | 81 | Observed 2026-11-21 · source benchlm:models | 81 | Observed 2026-11-21 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Math | 90 | Observed 2026-11-21 · source benchlm:models | 90 | Observed 2026-11-21 · 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 | 128.91 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 66 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · 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 | $0.25 | Observed 2026-11-21 · source benchlm:pricing |
| Cache write / 1M tokens | $12.50 | Observed 2026-11-21 · source modelsdev:catalog |
| 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 September 2026 launch page lists `claude-fable-5-1` at $10 input / $50 output per million tokens and cuts cache reads to $0.25 per million tokens. Anthropic estimates that lower cache-read rate reduces typical usage-based Fable workloads by about 25% and highly agentic workloads by as much as 45%; cache-write and Batch rates are not inferred from those estimates.

## 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

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

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| HLE (Humanity's Last Exam) | 65 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 49.2 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 93.7 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 59.1 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | 46.3 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 68.4 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 70.0 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HLE w/o tools (Humanity's Last Exam without tools) | 60.9 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 93.4 | Graduate-level science questions | Expert reasoning | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |
| MMLU-Pro (Vals) (MMLU-Pro, Vals AI run) | 92.4 | Academic multiple-choice questions | Broad academic knowledge | [Vals AI MMLU-Pro, Vals AI run leaderboard](https://www.vals.ai/benchmarks/mmlu_pro) |
| HealthBench (raw, Artificial Analysis) (Artificial Analysis HealthBench raw score) | 63.9 | 5,000 conversations | Health conversation evaluation | [HealthBench independent evaluation](https://artificialanalysis.ai/evaluations/healthbench) |
| HealthBench (length-adjusted, Artificial Analysis) (Artificial Analysis HealthBench length-adjusted score) | 57.2 | 5,000 conversations | Health conversation evaluation | [HealthBench independent evaluation](https://artificialanalysis.ai/evaluations/healthbench) |
| HealthBench Professional (length-adjusted, Artificial Analysis) (Artificial Analysis HealthBench Professional length-adjusted score) | 57.8 | 525 conversations | Health conversation evaluation | [HealthBench Professional independent evaluation](https://artificialanalysis.ai/evaluations/healthbench-professional) |
| HealthBench Professional (raw, Artificial Analysis) (Artificial Analysis HealthBench Professional raw score) | 69.2 | 525 conversations | Health conversation evaluation | [HealthBench Professional independent evaluation](https://artificialanalysis.ai/evaluations/healthbench-professional) |
| PhysicianBench | 61.0 | 100 EHR physician tasks | Clinical agent work | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SWE-bench Pro | 81.2 | 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) |
| SWE Multilingual | 89.1 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| SWE Multimodal (SWE-bench Multimodal) | 54.7 | Multimodal software engineering tasks | Frontier multimodal coding | [SWE-bench Multimodal](https://www.swebench.com/multimodal) |
| ProgramBench (ProgramBench: Can Language Models Rebuild Programs From Scratch?) | 87.6 | 200 program reconstruction tasks | Full-repository software architecture | [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://programbench.com/static/paper.pdf) |
| FrontierSWE v2 | 56.3 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | [FrontierSWE v2](https://www.frontierswe.com/blog/v2) |
| Bug Hunt Bench | 43.0 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | [Bug Hunt Bench method, caveats, and definitions](https://bughunt.productcompass.pm/method) |
| AA Coding Index (Artificial Analysis Coding Index) | 81.6 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 63.1 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 90.5 | Competitive programming problems (easy, medium, hard) | Frontier coding | [Vals AI LiveCodeBench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/lcb) |
| DeepSWE | 67.4 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |
| PostTrainBench v1.1 | 40.2 | Post-training Qwen3 1.7B and 4B, SmolLM3 3B, and Gemma3 4B | Frontier agent evaluation | [PostTrainBench v1.1 leaderboard and methodology](https://posttrainbench.com/?version=v1.1) |
| VulcanBench Frontier v4 | 91.8 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | [VulcanBench Frontier v4 leaderboard](https://vulcanbench.com/leaderboard.html) |
| FrontierCode 2.0 | 34.0 | 132 private software-engineering tasks | Frontier coding-agent quality | [FrontierCode 2.0](https://cognition.com/blog/frontier-code-2.0) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 90.175 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| FrontierMath v2 (Tier 4) (FrontierMath v2 Tier 4) | 87.805 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | [FrontierMath Tier 4 v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-1 (ARC-AGI-1 Semi-Private Evaluation) | 97.50 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | [ARC Prize leaderboard](https://arcprize.org/) |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 90 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 85.3 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 15.6 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| CritPt (Critical Physics Tasks) | 29.7 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |
| GraphWalks BFS 256K–1M | 65.0 | Breadth-first-search graph traversal on 200 problems with context lengths from 256K to 1M tokens. | Frontier agent evaluation | [Gemini 4 Argon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-argon) |
| STEM Professor Bench (Anthropic STEM Professor Bench) | 29.9 | 64 research problems | Research-level science | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |

### Multilingual

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GMMLU (Global MMLU) | 94.0 | Knowledge questions across 42 languages | Multilingual knowledge | [Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation](https://arxiv.org/abs/2412.03304) |
| MILU (Multi-task Indic Language Understanding Benchmark) | 93.0 | Knowledge tasks across 11 languages | Multilingual Indic knowledge | [MILU: A Multi-task Indic language understanding benchmark](https://arxiv.org/abs/2411.02538) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| DRACO (Data Research and Analysis with Complex Operations) | 87.7 | Agentic data research and analysis tasks | Professional data analysis | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified Pass@3 | 81.5 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified Pass³ (Toolathlon Verified Pass cubed) | 73.1 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified avg. turns (Toolathlon Verified average assistant turns) | 23.7 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Terminal-Bench 4.0 | 55.80 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.0](https://www.tbench.ai/news/terminal-bench-4-0) |
| Terminal-Bench-Science 0.1 | 52.6 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | [Terminal-Bench-Science 0.1](https://www.terminal-bench-science.ai/) |
| AA Briefcase (Artificial Analysis Briefcase) | 1671 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 59.4 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA Harvey LAB v1.0 (Artificial Analysis Harvey LAB-AA v1.0) | 93.0 | Legal agent tasks | Professional legal work | [Artificial Analysis Harvey LAB-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| AA ITBench (Artificial Analysis ITBench-AA) | 49.5 | IT incident-response tasks | Enterprise IT operations | [Artificial Analysis ITBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/itbench-aa) |
| AA Tau3 Banking (Artificial Analysis Tau3-Banking) | 47.2 | Banking tool-use workflows | Agentic banking workflows | [Artificial Analysis Tau3-Banking Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/tau3-banking) |
| GDPval-AA | 1765 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 62.7 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 58.0 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 52.0 | Terminal-based agent tasks | Agentic software engineering | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| GDP.pdf (Artificial Analysis GDP.pdf) | 26.2 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| AA-AnalystAgent (Artificial Analysis AnalystAgent) | 57.5 | Spreadsheet and document analysis questions | Business and data analysis | [AA-AnalystAgent Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-analyst-agent) |
| OSWorld 2.0 | 41.7 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | [OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://arxiv.org/abs/2606.29537) |
| Toolathlon-Verified | 77.8 | Verified multi-tool workflows | Advanced tool use | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| AutomationBench | 31.4 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 85.0 | Difficult terminal tasks | Frontier agentic | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |
| ApprenticeBench (ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job) | 72 | 100 vendor bills processed in sequence inside a simulated construction company | Long-horizon computer use with offline and online continual learning | [ApprenticeBench: a step change in AI's job readiness](https://neocognition.io/blog/apprentice-bench/) |
| CWE-bench v1 | 58.0 | Audit and patch held-out C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories | Frontier agent evaluation | [CWE-bench v1 leaderboard and methodology](https://cwe-bench.com/) |
| Harvey LAB-AA v1.1 | 6.4 | 120 private legal tasks across 24 practice areas | Professional legal work | [Harvey LAB-AA v1.1 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 10 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | [MazeBench Results](https://mazebench.com/blog?post=maze-bench-results) |
| Real-World Finance v2 (Anthropic Real-World Finance v2) | 1493 | 123 finance tasks | Professional finance work | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |
| AA-Briefcase (rubric) (AA-Briefcase v1.1, rubric pass rate) | 61.5 | Professional knowledge-work briefs | Professional knowledge work | [Artificial Analysis AA-Briefcase](https://artificialanalysis.ai/) |
| Remote Labor Index (Remote Labor Index (RLI)) | 17.9 | 240 freelance projects | End-to-end remote work | [Remote Labor Index](https://scale.com/leaderboard/rli) |
| RoboDojo Sim | 27.6 | Simulated robot-control tasks (count not published) | Embodied agent control | [Introducing Claude Fable 5.2 and Claude Mythos 5.2](https://www.anthropic.com/claude-fable-and-mythos-5-2) |
| WANDR (WANDR (Wide ANd Deep Research)) | 68.7 | 500 wide-search research tasks | Agentic search | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |
| Terminal-Bench 4.1 | 57.60 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.1](https://www.tbench.ai/news/terminal-bench-4-1) |
| OSWorld 2.1 (OSWorld 2.1 (all 108 tasks)) | 80.7 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | [OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1)](https://github.com/xlang-ai/OSWorld-V2/releases) |
| OSWorld 2.1 Offline (OSWorld 2.1 offline subset (82 tasks)) | 83.5 | 82 offline computer-use workflows | Long-horizon professional workflows | [OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1)](https://github.com/xlang-ai/OSWorld-V2/releases) |
| AA Cyber Index (Artificial Analysis Cyber Index) | 25.0 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | [Artificial Analysis Cyber Index](https://artificialanalysis.ai/evaluations/artificial-analysis-cyber-index) |
| CWE-Bench-AA (Artificial Analysis CWE-Bench-AA) | 50.8 | Real-world vulnerability patching tasks | Automated vulnerability remediation | [CWE-Bench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cwe-bench-aa) |
| DeepsecBench-AA (Artificial Analysis DeepsecBench-AA) | 23.5 | Vulnerability discovery in real codebases | Security code review | [DeepsecBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/deepsecbench-aa) |
| CyberGym-E2E-AA (Artificial Analysis CyberGym-E2E-AA) | 0.8 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | [CyberGym-E2E-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cybergym-e2e-aa) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Chartography (no tools) (Chartography without tools) | 42.6 | 100 specialized chart types | Professional chart reasoning | [Chartography](https://surgehq.ai/blog/chartography) |
| Chartography (tools) (Chartography with image and code tools) | 86.2 | 100 specialized chart types | Professional chart reasoning | [Chartography](https://surgehq.ai/blog/chartography) |
| BenchCAD Vision2Code (no tools) (BenchCAD Vision2Code voxel IoU without tools) | 0.437 | 1,000-file Vision2Code subset | Programmatic CAD generation | [BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD](https://arxiv.org/abs/2605.10865) |
| BenchCAD Vision2Code (tools) (BenchCAD Vision2Code voxel IoU with tools) | 0.843 | 1,000-file Vision2Code subset | Programmatic CAD generation | [BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD](https://arxiv.org/abs/2605.10865) |
| GDP.pdf (no tools) (GDP.pdf mean criteria pass rate without tools) | 85.4 | 100 professional document prompts | Professional document reasoning | [GDP.pdf](https://surgehq.ai/blog/gdp-pdf-can-100b-ai-models-master-the-documents-that-run-the-world) |
| GDP.pdf (tools) (GDP.pdf mean criteria pass rate with tools) | 85.1 | 100 professional document prompts | Professional document reasoning | [GDP.pdf](https://surgehq.ai/blog/gdp-pdf-can-100b-ai-models-master-the-documents-that-run-the-world) |
| OfficeQA | 80.2 | Historical Treasury Bulletin questions | Professional document reasoning | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Design Arena Website (Design Arena Website Elo) | 1302 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |
| OfficeQA Pro | 69 | Document and spreadsheet tasks | Enterprise grounded reasoning | [OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning](https://arxiv.org/abs/2603.08655) |
| ParseBench-1 (ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release)) | 77.81 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | [ParseBench: A Document Parsing Benchmark for AI Agents](https://arxiv.org/abs/2604.08538) |
| BenchCAD 2.1 (tools) (BenchCAD 2.1 Core, with tools) | 44.4 | BenchCAD 2.1 Core set | CAD generation | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |
| BenchCAD 2.1 (BenchCAD 2.1 Core, without tools) | 36.3 | BenchCAD 2.1 Core set | CAD generation | [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Gray Swan IPI (15 attempts) (Gray Swan Indirect Prompt Injection, attack success at 15 attempts) | 1.0 | Indirect prompt-injection attacks | Adversarial prompt injection | [Gemini 4 Argon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-argon) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SpireClimb (SpireClimb (Slay the Spire 1 and 2)) | 2.0 | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model | Maximum game difficulty, long-horizon computer use | [SpireClimb (Epoch AI)](https://epoch.ai/benchmarks/spireclimb) |
| Chess Puzzles (Chess Puzzles (Epoch AI)) | 48.0 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | [Chess Puzzles (Epoch AI)](https://epoch.ai/benchmarks/chess-puzzles) |
| Mystery Game Puzzles (Mystery Game Puzzles (Epoch AI)) | 58.0 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | [Mystery Game Puzzles (Epoch AI)](https://epoch.ai/benchmarks/mystery-game-puzzles) |
| Furniture Assembly (Furniture Assembly Benchmark (Epoch AI)) | 70.0 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | [Furniture Assembly Benchmark (Epoch AI)](https://epoch.ai/benchmarks/furniture-assembly) |
| EBR-bench (Earthborne Rangers (EBR-bench)) | 57.1 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | [Earthborne Rangers (EBR-bench), Epoch AI](https://epoch.ai/benchmarks/ebr-bench) |
| MirrorCode (MirrorCode (Epoch AI and METR)) | 93.3 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | [MirrorCode (Epoch AI)](https://epoch.ai/benchmarks/mirrorcode) |
| Epoch Automation Reports | 64.4 | 11 open-ended work tasks in five categories from Epoch AI's own work | Open-ended professional research and design work | [Epoch Automation Reports](https://epoch.ai/benchmarks/epoch-automation-reports) |
| Clocktower Bench (Clocktower Bench (Blood on the Clocktower)) | 1595 | 386 rated head-to-head games of Blood on the Clocktower (10 to 12 players) | Social deduction, deception and multi-agent reasoning | [Clocktower Bench leaderboard](https://clocktowerbench.com/) |
| Code2Video | 1536 | Creative briefs rendered as motion-graphics video | Code-driven motion design | [BenchLM](https://benchlm.ai/benchmarks/code2video) |
| Landing Page Arena | 1553 | 12 client briefs for small-business landing pages, rated by human votes | Marketing page design and copy | [BenchLM](https://benchlm.ai/benchmarks/landing-page-arena) |
| Chart Arena | 1581 | 13 chart briefs with small datasets, rated by human votes | Data visualisation | [BenchLM](https://benchlm.ai/benchmarks/chart-arena) |
| Joke Arena | 1548 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | [BenchLM](https://benchlm.ai/benchmarks/joke-arena) |
| Pelican Arena | 1677 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | [BenchLM](https://benchlm.ai/benchmarks/pelican-arena) |
| Landmark Arena | 1604 | 20 famous landmarks built as three.js web pages, rated by human votes | 3D scenes in browser code | [BenchLM](https://benchlm.ai/benchmarks/landmark-arena) |
| ASCII Arena | 1481 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | [BenchLM](https://benchlm.ai/benchmarks/ascii-arena) |
| Game Arena Go | 1601 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | [BenchLM](https://benchlm.ai/benchmarks/game-arena-go) |
| BabaIsBench (BabaIsBench (Baba Is You intro levels, pass@1)) | 100 | 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) | Rule-rewriting puzzles that need planning over many moves | [Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma)](https://quesma.com/blog/baba-is-bench/) |
| NYT Connections (NYT Connections LLM Benchmark (extended version)) | 90.0 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | [NYT Connections LLM Benchmark (Lech Mazur, GitHub)](https://github.com/lechmazur/nyt-connections) |
| StealthMark (StealthMark Intelligence Benchmarks (overall score)) | 62.9 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | [StealthMark: The AI Benchmark Explained (Stealth Models)](https://stealthmodels.com/stealthmark) |
| FrontierPhysics (End-to-End Physics Research Benchmark for AI Agents) | 11.3 | 56 research projects from 42 physicists across nine fields, three trials each (168 rollouts per setup) | Open-ended research projects that took their authors about 270 days on average | [FrontierPhysics: Evaluating Agents for End-to-End Physics Research (arXiv, November 4, 2026)](https://arxiv.org/abs/2611.06910) |
| HoneyBench (HoneyBench v0.2 (Goodhart Labs)) | 61.8 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | [HoneyBench v0.2](https://goodhartlabs.com/honeybench) |

## Independent scores (Epoch AI)

A second, independent score source: Epoch's own figures in Epoch's units, one line per model version Epoch evaluated (effort setting as Epoch labels it); higher is better. Not part of this site's capability scores or rank.

| Benchmark | Variant | Score | Unit | Epoch date | Evidence |
| --- | --- | --- | --- | --- | --- |
| FrontierMath Tiers 1-3 (v2) | max | 0.9018 | fraction (0–1) | 2026-09-01 | Last good 2026-11-20 · source epoch:benchmarks |
| FrontierMath Tier 4 (v2) | max | 0.878 | fraction (0–1) | 2026-09-01 | Last good 2026-11-20 · source epoch:benchmarks |
| SimpleQA Verified | max | 0.708 | fraction (0–1) | 2026-09-01 | Last good 2026-11-20 · source epoch:benchmarks |

Source: [Epoch AI, CC BY 4.0](https://epoch.ai/benchmarks) ([licence](https://creativecommons.org/licenses/by/4.0/)). Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

| Event | Type | Confirmation | Announced | Effective | Replacement | Source |
| --- | --- | --- | --- | --- | --- | --- |
| Claude Fable 5.1 and Claude Mythos 5.1 | Release | confirmed | Unavailable | 2026-09-01 | — | [Anthropic](https://www.anthropic.com/claude-fable-and-mythos-5-1) |

## 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.
