# Claude Fable 5.1High > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-fable-5-1-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-fable-5-1-high. Anthropic Canonical URL: https://benchize.com/models/claude-fable-5-1-high Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Anthropic ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 50.34% | — | 14 / 125 | $5.27 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5034 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5512 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 5.2741 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort high sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Fable 5.1 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Fable%205.1/high/main` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 62.68% | — | 14 / 125 | $4.28 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6268 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6815 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 4.2833 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort high sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Fable 5.1 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Fable%205.1/high/extended` | | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 3.76 | 95% CI 3.67–3.85 | 1 / 50 | — | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 3.756462887159027 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.9340839066310491 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 3.67–3.85 bootstrapSamples 300 confidenceInterval95 ["3.6748593284624396","3.8502845844526776"] sourceRank 1 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label Claude Fable 5.1 (high) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/0` | | | | | | | | | [TapTap Maker heldout](https://benchize.com/benchmarks/taptap-maker%3Aheldout.md) | 75.94% | Range 74.51–77.37% | 2 / 26 | — | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.7594 \| score_fraction \| reported \| Higher is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness claude Reasoning effort high reasoningMode Not reported ### Reported statistics Uncertainty Reported interval: 74.51–77.37% interval [0.7451,0.7737] intervalMethod bootstrap-case rank 2 rankInterval [1,4] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label claude-fable-5-1 Observed 2026-10-21T16:33:19.620Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/heldout/1` | | | | | | | | | [TapTap Maker public](https://benchize.com/benchmarks/taptap-maker%3Apublic.md) | 85.53% | Range 84.83–86.22% | 2 / 26 | $3.76 | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.8553 \| score_fraction \| reported \| Higher is better \| \| `cost_per_case` \| 3.7588 \| USD \| per_case \| Lower is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness claude Reasoning effort high reasoningMode always-on ### Reported statistics Uncertainty Reported interval: 84.83–86.22% interval [0.8483,0.8622] intervalMethod bootstrap-case rank 2 rankInterval [1,4] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label claude-fable-5-1 Observed 2026-10-21T16:33:19.620Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/public/1` | | | | | | | | | [Terminal-Bench 2.1 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Amedium.md) | 85.46% | SE ±1.05 pp | 5 / 43 | $2.65 | 809.67source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.455 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.649676 \| USD \| per_test \| Lower is better \| \| `latency` \| 809.665 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.05 pp sourcePopulation 76 stderr 1.05 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/medium/anthropic~1claude-fable-5-1` | | | | | | | | | [Terminal-Bench 2.1 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aeasy.md) | 100% | SE ±0 pp | 1 / 43 | $1.74 | 11,132.9source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.741133 \| USD \| per_test \| Lower is better \| \| `latency` \| 11132.898 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 76 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/easy/anthropic~1claude-fable-5-1` | | | | | | | | | [Terminal-Bench 2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aoverall.md) | 85.02% | SE ±0.99 pp | 4 / 43 | $3.07 | 500.36source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.019 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.074796 \| USD \| per_test \| Lower is better \| \| `latency` \| 500.355 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.99 pp sourcePopulation 76 stderr 0.991 tokenTotals {"cache_read_tokens":19902668,"cache_write_tokens":1985257,"input_tokens":21892452,"output_tokens":965107,"reasoning_tokens":472161} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/overall/anthropic~1claude-fable-5-1` | | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 88.75% | — | 20 / 212 | 1.67usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8875 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 1.6673061666666666 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-claude-fable-5-1 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-fable-5-1-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Fable 5.1 (High) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/223` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 96% | — | 29 / 213 | 0.52usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.96 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.5169491 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-claude-fable-5-1 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-fable-5-1-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Fable 5.1 (High) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/221` | | | | | | | | | [ArXivMath 08/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--august.md) | 87.72% | 95% CI 81.69–93.75% | 4 / 11 | 12.77usd per problem | — | [matharena · arxiv--august](https://matharena.ai/competition_tables/arxiv--august) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.72 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 12.77 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--august predicted false Reasoning effort high sourceModelName Claude-Fable-5.1 (high) sourceModelVersion anthropic/fable_51_high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 81.69–93.75% confidenceInterval95 6.03 problems 57 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--august) Source matharena Original model label Claude-Fable-5.1 (high) Source version arxiv--august Observed 2026-10-21T16:52:30.283Z Evidence SHA-256 `5924e5ecc15ff087ec1504b1e4ac44408b005c4f70e81e0d2184f930383a963c` Source locator `/table/rows/3` | | | | | | | | | [MirrorCode](https://benchize.com/benchmarks/epoch-ai%3Amirrorcode.md) | 73.3% | SE ±9.17 pp | 2 / 8 | — | — | [epoch ai · MirrorCode](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.733 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.733 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion MirrorCode reasoningBudget Not reported Reasoning effort high sourceModelVersion claude-fable-5-1_high ### Reported statistics Uncertainty Standard error: ±9.17 pp standardError 0.0917 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) Source epoch ai Original model label claude-fable-5-1 Source version MirrorCode Evaluated 2026-09-10T13:19:30.449Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5c31ffdeca24dd23e8d1dc40da67f2ec3e2e6f6d63e1a2b2791239e29f5b454e` Source locator `/rows/1` | | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,333.4 | Range 2,279.2–2,385 | 9 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2333.4 \| rating \| reported \| Higher is better \| \| `overall` \| 83.41 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 74.35 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 83.65 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 80.93 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 80.94 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 95.82 \| source_score \| rubric \| Higher is better \| \| `slop` \| 85.63 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 96.91 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 85.09 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 80.84 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 79.79 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 82.72 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort unknown scoreScope 10_task_current sourceConfiguration claude-fable-5-1 thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 2,279.2–2,385 interval [2279.2,2385] rank 9 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Fable 5.1 (high) Evaluated 2026-10-08 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/8` | | | | | | | | | [BrokenArXiv 08/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--august.md) | 79.76% | 95% CI 69.24–90.28% | 3 / 11 | 19.57usd per problem | — | [matharena · arxiv_false--august](https://matharena.ai/competition_tables/arxiv_false--august) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.76 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 19.57 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--august predicted false Reasoning effort high sourceModelName Claude-Fable-5.1 (high) sourceModelVersion anthropic/fable_51_high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 69.24–90.28% confidenceInterval95 10.52 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--august) Source matharena Original model label Claude-Fable-5.1 (high) Source version arxiv_false--august Observed 2026-10-21T16:52:25.683Z Evidence SHA-256 `1facf024f36359a3fcf069fc3b747d7fbf6aeec67c7949ed674b50ec0447a209` Source locator `/table/rows/2` | | | | | | | | | [Terminal-Bench 2.1 / hard](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Ahard.md) | 82.22% | SE ±1.11 pp | 4 / 43 | $4.03 | 1,484.39source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.222 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.032005 \| USD \| per_test \| Lower is better \| \| `latency` \| 1484.386 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 76 stderr 1.111 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/hard/anthropic~1claude-fable-5-1` | | | | | | | | --- Cite as: Claude Fable 5.1High — Benchize, https://benchize.com/models/claude-fable-5-1-high (retrieved 2026-10-21)