Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Anthropic · Proprietary · rank 1 · bench-align-v5
Claude Fable 5.2 is built for coding and reasoning. It ranks in the top quarter for knowledge (top 1% of 283 scored models) and math (top 1% of 110 scored models), by BenchLM's published scores. It accepts text, images and PDFs and produces text.
Every published price component, including cache reads and writes.
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.
Lifecycle events the source associates with this model, plus what this profile does not claim.
Claude Fable 5.2 by Anthropic scores 93.2 overall, costs $8.00 per 1M input tokens and $40.00 per 1M output tokens, and carries a context window of 1M tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
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: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 228.89 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 111 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Plans from the model's maker, and the API providers that list this exact model today. Links leave ModelScale; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| HLE Humanity's Last Exam | 74.2 | #1 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 64.6 | #1 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-HLE Artificial Analysis Humanity's Last Exam | 74.3 | #1 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 66.8 | #1 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 79.1 | #1 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 59.3 | #132 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 73.2 | #1 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| HealthBench (raw, Artificial Analysis) Artificial Analysis HealthBench raw score | 58.8 | #5 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench length-adjusted score | 59.6 | #2 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench Professional (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench Professional length-adjusted score | 67.7 | #1 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| HealthBench Professional (raw, Artificial Analysis) Artificial Analysis HealthBench Professional raw score | 71.1 | #2 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| PhysicianBench PhysicianBench | 64.4 | #2 | 100 EHR physician tasks | Clinical agent work | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SWE-bench Pro SWE-bench Pro | 93 | #1 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| SWE Multilingual SWE Multilingual | 96.6 | #1 | Multilingual software-engineering tasks | Professional software engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
| SWE Multimodal SWE-bench Multimodal | 74.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 95.088 | #1 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 100.000 | #1 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ARC-AGI-3 Abstraction and Reasoning Corpus for AGI v3 | 65.66 | #2 | Interactive game-like tasks with hidden rules | Frontier agentic reasoning | ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence |
| AA-LCR Artificial Analysis Long Context Reasoning | 83.3 | #13 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 43.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GMMLU Global MMLU | 96.0 | #1 | Knowledge questions across 42 languages | Multilingual knowledge | Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation |
| MILU Multi-task Indic Language Understanding Benchmark | 94.1 | #1 | Knowledge tasks across 11 languages | Multilingual Indic knowledge | MILU: A Multi-task Indic language understanding benchmark |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| DRACO Data Research and Analysis with Complex Operations | 87.7 | #2 | Agentic data research and analysis tasks | Professional data analysis | Claude Opus 5 System Card |
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 67.60 | #3 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| Terminal-Bench-Science 0.1 Terminal-Bench-Science 0.1 | 74.6 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chartography (no tools) Chartography without tools | 73.4 | #1 | 100 specialized chart types | Professional chart reasoning | Chartography |
| Chartography (tools) Chartography with image and code tools | 91.6 | #1 | 100 specialized chart types | Professional chart reasoning | Chartography |
| OfficeQA OfficeQA | 83.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SpireClimb SpireClimb (Slay the Spire 1 and 2) | 15.3 | #5 | 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) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 79.0 | #1 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 90.0 |
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). They are not part of this site’s capability scores or rank.
| Benchmark | Variant | Score | Epoch date | Evidence |
|---|---|---|---|---|
| GPQA Diamond Accuracy on graduate-level science multiple-choice questions (best score across scorers). Unit: fraction (0–1); higher is better. | max | 0.9388 ± 0.0163 | 2026-11-06 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | max | 0.9509 ± 0.0128 | 2026-11-06 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | max | 1 ± 0 | 2026-11-06 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | max | 0.94 ± 0.0075 | 2026-11-06 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
| #1 |
| Multimodal software engineering tasks |
| Frontier multimodal coding |
| SWE-bench Multimodal |
| ProgramBench ProgramBench: Can Language Models Rebuild Programs From Scratch? | 85.6 | #4 | 200 program reconstruction tasks | Full-repository software architecture | ProgramBench: Can Language Models Rebuild Programs From Scratch? |
| FrontierSWE v2 FrontierSWE v2 | 69.9 | #1 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 58.0 | #2 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| AA-SciCode Artificial Analysis SciCode | 67.7 | #1 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| DeepSWE DeepSWE | 74.3 | #10 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| VulcanBench Frontier v4 VulcanBench Frontier v4 | 93.8 | #1 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | VulcanBench Frontier v4 leaderboard |
| FrontierCode 2.0 FrontierCode 2.0 | 50.2 | #1 | 132 private software-engineering tasks | Frontier coding-agent quality | FrontierCode 2.0 |
| #5 |
| Long, fragmented medical-record reasoning |
| Long-context medical reasoning |
| Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 35.4 | #1 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| ARC-AGI-3 Provider Adapter ARC-AGI-3 Semi-Private: Provider Adapter harness | 94.90 | #7 | — | — | ARC Prize verified ARC-AGI-3 results |
| STEM Professor Bench Anthropic STEM Professor Bench | 61.8 | #1 | 64 research problems | Research-level science | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| #3 |
| 70 expert-curated scientific research workflows |
| Frontier scientific research workflows |
| Terminal-Bench-Science 0.1 |
| AA Briefcase Artificial Analysis Briefcase | 1785 | #3 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 76.4 | #5 | Business-process automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| GDPval-AA GDPval-AA | 1831 | #6 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 59.6 | #7 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 24.2 | #20 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AutomationBench AutomationBench | 51.4 | #12 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Harvey LAB-AA v1.1 Harvey LAB-AA v1.1 | 7.2 | #6 | 120 private legal tasks across 24 practice areas | Professional legal work | Harvey LAB-AA v1.1 Benchmark Leaderboard |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 22 | #2 | 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 |
| Real-World Finance v2 Anthropic Real-World Finance v2 | 1637 | #1 | 123 finance tasks | Professional finance work | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| AA-Briefcase (rubric) AA-Briefcase v1.1, rubric pass rate | 66.1 | #1 | Professional knowledge-work briefs | Professional knowledge work | Artificial Analysis AA-Briefcase |
| Remote Labor Index Remote Labor Index (RLI) | 41.3 | #1 | 240 freelance projects | End-to-end remote work | Remote Labor Index |
| RoboDojo Sim RoboDojo Sim | 64.9 | #1 | Simulated robot-control tasks (count not published) | Embodied agent control | Introducing Claude Fable 5.2 and Claude Mythos 5.2 |
| WANDR WANDR (Wide ANd Deep Research) | 82.1 | #1 | 500 wide-search research tasks | Agentic search | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| CWE-bench CWE-bench v2 | 75.0 | #1 | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks | Frontier agent evaluation | CWE-bench v2 leaderboard and methodology |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 65.80 | #1 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| OSWorld 2.1 Offline OSWorld 2.1 offline subset (82 tasks) | 89.3 | #1 | 82 offline computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| MKA Multimodal Knowledge Agent Benchmark | 56.6 | #1 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| #1 |
| Historical Treasury Bulletin questions |
| Professional document reasoning |
| Claude Opus 5 System Card |
| Design Arena Website Design Arena Website Elo | 1348 | #3 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| OfficeQA Pro OfficeQA Pro | 72.9 | #1 | Document and spreadsheet tasks | Enterprise grounded reasoning | OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning |
| BenchCAD 2.1 (tools) BenchCAD 2.1 Core, with tools | 83.5 | #1 | BenchCAD 2.1 Core set | CAD generation | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| BenchCAD 2.1 BenchCAD 2.1 Core, without tools | 75.4 | #1 | BenchCAD 2.1 Core set | CAD generation | Claude Fable 5.2 and Claude Mythos 5.2 system card |
| #2 |
| 100 single-best-move positions from an undisclosed game |
| Unfamiliar game positions, single best move |
| Mystery Game Puzzles (Epoch AI) |
| Furniture Assembly Furniture Assembly Benchmark (Epoch AI) | 90.0 | #1 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | Furniture Assembly Benchmark (Epoch AI) |
| EBR-bench Earthborne Rangers (EBR-bench) | 90.5 | #2 | 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 |
| Game Arena Go Game Arena Go | 1877 | #1 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | BenchLM |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 97.3 | #7 | 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) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 11.9 | #21 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |