Claude Fable 5.1 Benchmarks, Specifications & Availability
Explore Claude Fable 5.1 from Anthropic: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.
Compare Claude Fable 5.1 with other models →Explore data coverage
Published specifications
- Provider
- Anthropic
- Access
- Proprietary
- License
- Proprietary
- Context window
- 1M
- Total parameters
- Not published
- Active parameters
- Not published
- Released
- 2026-09-01
- Modalities
- text, image, file
- Family
- Claude Fable 5
Model card · Announcement · Website · OpenRouter
Model notes
Generally available Fable 5.1; Mythos 5.1 is same base under stricter safeguards.
Pricing · OpenRouter
Dated cached OpenRouter rates in USD per 1M tokens. Open the dashboard for live enhancements. Per-metric endpoint minima can refer to different providers; they are not a guaranteed combined rate from one endpoint.
| Tier | Input / 1M | Output / 1M | Cached input / 1M | Cache write / 1M | Date & source |
|---|---|---|---|---|---|
| Default | [object Object] | [object Object] | [object Object] | [object Object] | 2026-10-03 · OpenRouter source |
Recorded pricing notes
min-healthy endpoint minima 2026-10-01; min-healthy endpoint minima 2026-10-01; min-healthy endpoint minima 2026-10-02; min-healthy endpoint minima 2026-10-03
Official / vendor benchmarks
Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| ARC-AGI-1 | 97.5%unknown effort | All 1 recorded result & sources97.5% · raw 97.5 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported in OpenAI GPT-6 Astra comparison table https://openai.com/index/gpt-6-astra/ |
| ARC-AGI-2 | 90%unknown effort | All 1 recorded result & sources90% · raw 90 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported in OpenAI GPT-6 Astra comparison table https://openai.com/index/gpt-6-astra/ |
| AutomationBench v1.0.6 | 31.4%unknown effort | All 2 recorded results & sources31.4% · raw 31.4 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/31.4% · raw 31.4 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology | Same value as current headline; kept as corroboration, non-headline. https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| DeepSWE v1.1 | 67.4%unknown effort | All 2 recorded results & sources67.4% · raw 67.4 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/67.4% · raw 67.4 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology | Same value as current headline; kept as corroboration, non-headline. https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| ExploitGym | 30.4%unknown effort | All 1 recorded result & sources30.4% · raw 30.4 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/ |
| FrontierCode 1.1 Extended | 63.6%unknown effort | All 1 recorded result & sources63.6% · raw 63.6 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported in OpenAI GPT-6 Astra comparison table https://openai.com/index/gpt-6-astra/ |
| FrontierCode 1.1 Main | 50.3%unknown effort | All 2 recorded results & sources50.9% · raw 50.9 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported in OpenAI GPT-6 Astra comparison table | Demoted 2026-09-25: duplicate of headline from Anthropic Claude Opus 5.5 announce (anthropic.com/claude-opus-5-5); model vendor's own (Anthropic) figure preferred over peer-vendor OpenAI comparison table (rule a); Anthropic source is also later-dated (2026-09-22). Values differ (50.9 here vs 50.3 Anthropic); not reconciled. https://openai.com/index/gpt-6-astra/50.3% · raw 50.3 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-5 |
| FrontierMath Tier 4 | 87.8%unknown effort | All 1 recorded result & sources87.8% · raw 87.8 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/ |
| GPQA Diamond | 93.7%unknown effort | All 1 recorded result & sources93.7% · raw 93.7 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/ |
| HealthBench Professional | 58.1%unknown effort | All 1 recorded result & sources58.1% · raw 58.1 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI https://openai.com/index/gpt-6-astra/ |
| Humanity's Last Exam (w/ tools) | 65.6%unknown effort | All 2 recorded results & sources65% · raw 65 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI | Demoted 2026-09-25: duplicate of headline from Anthropic Claude Opus 5.5 announce (anthropic.com/claude-opus-5-5); model vendor's own (Anthropic) figure preferred over peer-vendor OpenAI comparison table (rule a); Anthropic source is also later-dated (2026-09-22). Values differ (65.0 here vs 65.6 Anthropic); not reconciled. source_type relabeled official→vendor-comparison (OpenAI reporting an Anthropic model). https://openai.com/index/gpt-6-astra/65.6% · raw 65.6 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-5 |
| Terminal-Bench 4.0 | 55.8%unknown effort | All 3 recorded results & sources55.8% · raw 55.8 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-03 As reported by OpenAI GPT-6 Astra announcement table | Demoted 2026-09-25: duplicate of headline from Anthropic Claude Opus 5.5 announce (anthropic.com/claude-opus-5-5); model vendor's own (Anthropic) figure preferred over peer-vendor OpenAI comparison table (rule a); Anthropic source is also later-dated (2026-09-22); same value. source_type relabeled official→vendor-comparison (OpenAI reporting an Anthropic model). https://openai.com/index/gpt-6-astra/55.8% · raw 55.8 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-557.9% · raw 57.9 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology | Differs from current headline 55.8 (spillover); kept with provenance, non-headline. https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Terminal-Bench Science 0.1 | 52.6%unknown effort | All 3 recorded results & sources52.6% · raw 52.6 % Headline · unknown effort · Own vendor Source/record date: 2026-09-01 Anthropic announcement; also Simon Willison summary https://www.anthropic.com/claude/fable52.6% · raw 52.6 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce | Demoted 2026-09-25: duplicate of headline from Anthropic Claude Fable launch page (anthropic.com/claude/fable); model's own launch announcement preferred over later spillover in Opus 5.5 comparison table (rule a); same value. https://www.anthropic.com/claude-opus-5-552.6% · raw 52.6 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology | Same value as current headline; kept as corroboration, non-headline. https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| CursorBench 4.0 | 51.8%unknown effort | All 1 recorded result & sources51.8% · raw 51.8 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-5 |
| GDPval-AA 2.1 | 1735unknown effort | All 1 recorded result & sources1735 · raw 1735 Elo Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-5 |
| AutomationBench | 31.4%unknown effort | All 1 recorded result & sources31.4% · raw 31.4 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce (Zapier) https://www.anthropic.com/claude-opus-5-5 |
| OSWorld 2.0 | 77.9%unknown effort | All 2 recorded results & sources80.7% · raw 80.7 % Alternative · unknown effort · Peer vendor Source/record date: 2026-09-22 OSWorld 2.0 partial; as reported by Anthropic Opus 5.5 announce; demoted as headline after Fable own-page figure harvest https://www.anthropic.com/claude-opus-5-577.9% · raw 77.9 % Headline · unknown effort · Own vendor Source/record date: Not recorded from chart/figure Anthropic Fable page; OSWorld 2.0 partial (strict 41.7% also shown) https://www.anthropic.com/claude/fable |
| Chartography (w/ tools) | 88.4%unknown effort | All 1 recorded result & sources88.4% · raw 88.4 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-22 As reported by Anthropic Opus 5.5 announce https://www.anthropic.com/claude-opus-5-5 |
| GDPval-AA v2 | 1853unknown effort | All 1 recorded result & sources1853 · raw 1853 Elo Headline · unknown effort · Own vendor Source/record date: Not recorded from chart/figure Anthropic Fable page benchmark table; GDPval-AA v2 Elo https://www.anthropic.com/claude/fable |
| Humanity's Last Exam | 60.9%unknown effort | All 1 recorded result & sources60.9% · raw 60.9 % Headline · unknown effort · Own vendor Source/record date: Not recorded from chart/figure Anthropic Fable page; Humanity's Last Exam no tools https://www.anthropic.com/claude/fable |
| CursorBench 3.2.0 | 73.4%unknown effort | All 1 recorded result & sources73.4% · raw 73.4 % Headline · unknown effort · Own vendor Source/record date: Not recorded from chart/figure Anthropic Fable page; CursorBench 3.2.0 (distinct from 4.0) https://www.anthropic.com/claude/fable |
| AA Intelligence Index (vendor-cited) | 66unknown effort | All 1 recorded result & sources66 · raw 66 index Headline · unknown effort · Peer vendor Source/record date: Not recorded from chart/figure as reported on Ling-3.0-flash-VL HF card AA Index v4.1.1 chart (peer spillover); Claude Fable 5.1 (max with fallback) https://huggingface.co/inclusionAI/Ling-3.0-flash-VL |
| FrontierSWE | 56.3%unknown effort | All 1 recorded result & sources56.3% · raw 56.3 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-28 As reported by Anthropic (Sonnet 5.5 card); Proximal harness https://www.anthropic.com/claude-sonnet-5-5-system-card |
| Global MMLU | 94%max effort | All 1 recorded result & sources94% · raw 94 % Headline · max effort · Peer vendor Source/record date: 2026-09-28 As reported by Anthropic (Sonnet 5.5 card) https://www.anthropic.com/claude-sonnet-5-5-system-card |
| MILU | 93%max effort | All 1 recorded result & sources93% · raw 93 % Headline · max effort · Peer vendor Source/record date: 2026-09-28 As reported by Anthropic (Sonnet 5.5 card) https://www.anthropic.com/claude-sonnet-5-5-system-card |
| Vals Index | 65.8%unknown effort | All 1 recorded result & sources65.8% · raw 65.8 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Vals Finance Agent v2 | 58.9%unknown effort | All 1 recorded result & sources58.9% · raw 58.9 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Harvey Legal Agent Benchmark | 6.7%unknown effort | All 1 recorded result & sources6.7% · raw 6.7 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| FrontierSWE v2 | 56.3%unknown effort | All 1 recorded result & sources56.3% · raw 56.3 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Vibe Code Bench | 90.3%unknown effort | All 1 recorded result & sources90.3% · raw 90.3 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| PostTrainBench | 40.2%unknown effort | All 1 recorded result & sources40.2% · raw 40.2 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| LABBench 2 | 68.6%unknown effort | All 1 recorded result & sources68.6% · raw 68.6 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| RiemannBench | 65.6%unknown effort | All 1 recorded result & sources65.6% · raw 65.6 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| GraphWalks up to 128k BFS F1 | 91.4 f1unknown effort | All 1 recorded result & sources91.4 f1 · raw 91.4 f1 Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| GraphWalks 256k-1M BFS F1 | 65 f1unknown effort | All 1 recorded result & sources65 f1 · raw 65 f1 Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Chartography | 46.2%unknown effort | All 1 recorded result & sources46.2% · raw 46.2 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| LVBench | 79.7%unknown effort | All 1 recorded result & sources79.7% · raw 79.7 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| CWE-bench v1 | 58%unknown effort | All 1 recorded result & sources58% · raw 58 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif |
| Gray Swan IPI | 1%unknown effort | All 1 recorded result & sources1% · raw 1 % Headline · unknown effort · Peer vendor Source/record date: 2026-09-30 As reported by Google Gemini 4 Argon chart; peer harness notes in Google eval methodology https://storage.googleapis.com/gweb-uniblog-publish-prod/images/gemini_4_cyber_evals_gray_swan_i.width-1200.format-webp.webp |
Independent evaluators
Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.
| Benchmark / evaluator | Headline score | Evidence |
|---|---|---|
| Intelligence Index · Artificial Analysis | 53max effort | All 5 recorded results & sources53 · raw 53 index Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-153 · raw 53 index Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-xhigh51 · raw 51 index Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-high49 · raw 49 index Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-medium47 · raw 47 index Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-low |
| Cost per Intelligence Index task · Artificial Analysis | $7.63max effort | All 5 recorded results & sources$7.63 · raw 7.63 USD Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1$5.98 · raw 5.98 USD Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-xhigh$3.91 · raw 3.91 USD Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-high$2.98 · raw 2.98 USD Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-medium$2.37 · raw 2.37 USD Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. https://artificialanalysis.ai/models/claude-fable-5-1-low |
| Output speed · Artificial Analysis | 68 tok/smax effort | All 5 recorded results & sources68 tok/s · raw 68 tok/s Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/claude-fable-5-166 tok/s · raw 66 tok/s Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/claude-fable-5-1-xhigh54 tok/s · raw 54 tok/s Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/claude-fable-5-1-high54 tok/s · raw 54 tok/s Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/claude-fable-5-1-medium53 tok/s · raw 53 tok/s Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; with fallback reasoning configuration. Median output tokens/s; leaderboard rounds to whole tokens. https://artificialanalysis.ai/models/claude-fable-5-1-low |
| Vals Index · Vals AI | 65.8%unknown effort | All 1 recorded result & sources65.8% · raw 65.83 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Cost/test $28.71. https://www.vals.ai/benchmarks/vals_index |
| Bugs fixed /105 · Bug Hunt Bench | 43 fixesmax effort | All 5 recorded results & sources43 fixes · raw 43 fixes Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code; effort max; 1 runs; evaluation 2026-09-01. Best documented score for this effort in Oct 1 README. Headline: best documented model run. https://github.com/phuryn/bug-hunt-bench33 fixes · raw 33 fixes Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code; effort high; 1 runs; evaluation 2026-09-01. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench29 fixes · raw 29 fixes Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code; effort low; 1 runs; evaluation 2026-09-02. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench29 fixes · raw 29 fixes Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code; effort xhigh; 1 runs; evaluation 2026-09-10. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench21 fixes · raw 21 fixes Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Harness: Claude Code; effort medium; 1 runs; evaluation 2026-09-10. Best documented score for this effort in Oct 1 README. https://github.com/phuryn/bug-hunt-bench |
| Pass Rate · MCP Atlas (Scale Labs) | 87.2%unknown effort | All 1 recorded result & sources87.2% · raw 87.2 % Headline · unknown effort · Independent evaluator Source/record date: 2026-09-23 Scale Labs Performance Comparison chart (Fable 5.1); ±2.05 CI https://labs.scale.com/leaderboard/mcp_atlas |
| Vibe Code Bench v1.1 · Vals AI | 90.3%unknown effort | All 1 recorded result & sources90.3% · raw 90.26 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Refreshed from current Vals leaderboard. Harness: OpenHands. Cost/test $33.37. https://www.vals.ai/benchmarks/vibe-code |
| CUDA board % of roofline · KernelBench (community board) | 48.4%max effort | All 1 recorded result & sources48.4% · raw 48.4 % Headline · max effort · Independent evaluator Source/record date: 2026-09-23 CUDA deck 4/4 pass; Mega 22.95×; or-fable max harness https://kernelbench.com/models/claude-fable-5-1 |
| ARC-AGI-1 · ARC Prize | 97.5%max effort | All 5 recorded results & sources97.5% · raw 97.5 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/anthropic-claude-fable-5-196.5% · raw 96.5 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-196% · raw 96 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-194.5% · raw 94.5 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-190% · raw 90 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1 |
| ARC-AGI-2 · ARC Prize | 90%max effort | All 5 recorded results & sources90% · raw 90 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/anthropic-claude-fable-5-190% · raw 90 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-188.8% · raw 88.8 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-186.3% · raw 86.3 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-178.3% · raw 78.3 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1 |
| AA-Omniscience Index · Artificial Analysis | 43max effort | All 1 recorded result & sources43 · raw 43 index Headline · max effort · Independent evaluator Source/record date: 2026-09-23 AA-Omniscience Index; Adaptive Reasoning Max Effort Default Fallback https://artificialanalysis.ai/evaluations/omniscience |
| GDPval-AA Elo · Artificial Analysis | 1735max effort | All 1 recorded result & sources1735 · raw 1735 Elo Headline · max effort · Independent evaluator Source/record date: 2026-09-23 GDPval-AA v2.1 Elo; Claude Fable 5.1 Adaptive Reasoning Max Effort Default Fallback https://artificialanalysis.ai/evaluations/gdpval-aa |
| Money gain · Andon Labs | $4921.56unknown effort | All 1 recorded result & sources$4921.56 · raw 4921.56 $ Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Vending-Bench 2 net gain = final_value in the page public vb2 data module minus $500 starting balance. Full 66-model source checked. https://andonlabs.com/evals/vending-bench-2 |
| Blueprint Bench · Andon Labs | 41.9%unknown effort | All 1 recorded result & sources41.9% · raw 41.9 % Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Blueprint-Bench 2 connectivity similarity; published fractional score multiplied by 100. https://andonlabs.com/evals/blueprint-bench-2 |
| Average Score · WeirdML v3 | 26%xhigh effort | All 1 recorded result & sources26% · raw 25.97 % Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Claude Fable 5.1 (xhigh); harness claude_code 2.1.270; values from prepared data JSON; raw 0.259702; official 80/20 aggregate (area 500k-50M tokens + final best) https://htihle.github.io/weirdml.html |
| Final Best Score · WeirdML v3 | 43.5%xhigh effort | All 1 recorded result & sources43.5% · raw 43.53 % Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Claude Fable 5.1 (xhigh); harness claude_code 2.1.270; values from prepared data JSON; raw 0.435272; mean final best effective score https://htihle.github.io/weirdml.html |
| Cost / Run · WeirdML v3 | $31.93xhigh effort | All 1 recorded result & sources$31.93 · raw 31.93 USD Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-02 WeirdML variant Claude Fable 5.1 (xhigh); harness claude_code 2.1.270; values from prepared data JSON; mean API cost per run, same task weighting as scores https://htihle.github.io/weirdml.html |
Read how we select and source scores or the comparison guide.