Claude Fable 5 · High

• Cognition · 17.9% direct comparison weight · independent of the model provider
• SWE-rebench · 16.9% direct comparison weight · independent of the model provider
• ARC Prize · 16.1% direct comparison weight · independent of the model provider
• Scale · 13.6% direct comparison weight · independent of the model provider
• Epoch AI · 12.6% direct comparison weight · independent of the model provider
• Terminal-Bench · 12.2% direct comparison weight · independent of the model provider
• Datacurve · 10.5% direct comparison weight · independent of the model provider

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

DeepSWE v1.1 review: Epoch AI reported grading errors in at least 23 of 113 tasks. These published results remain included. Review their limitations in Epoch's review when interpreting this evidence.

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Across all collected settings for this model: 288 observations, 91 contributing, 2 matched without graph weight and 195 excluded. Counts do not establish rank eligibility.

• 6 · Benchmark family or source protocol has not been reviewed
• 1 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
• 2 · Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking
• 4 · Evaluator has not been reviewed for independent admission
• 1 · The task-summary mean 47.20200% differs from the published headline mean@5 46.96449%; the headline score is retained.
• 36 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
• 5 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.
• 41 · Supporting evidence outside the reviewed capability core
• 1 · Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
• 3 · No matched opponent in this evaluation unit
• 1 · Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence.
• 9 · The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs.
• 15 · No matched, identified effort unit; duplicates and unnamed comparators do not add evidence
• 7 · Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison.
• 1 · Kimi K3 Evaluation Details cites GLM release blog or Vals AI, per model; retain as published context, not a new Moonshot comparison.
• 1 · Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison.
• 1 · Kimi K3 Evaluation Details cites FrontierSWE leaderboard; retain as published context, not a new Moonshot comparison. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
• 1 · Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison.
• 1 · Kimi K3 Evaluation Details cites official Agents Last Exam leaderboard; retain as published context, not a new Moonshot comparison.
• 1 · Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.
• 3 · Kimi K3 Evaluation Details cites Vals AI; retain as published context, not a new Moonshot comparison.
• 8 · Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.
• 2 · The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation. The source states that Fable 5 results may involve fallback execution; an exact configuration is not established.
• 23 · The source states that Fable 5 results may involve fallback execution; an exact configuration is not established.
• 1 · The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation. The source states that Fable 5 results may involve fallback execution; an exact configuration is not established. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
• 1 · Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit. Composite index excluded to avoid double counting its ingredients.
• 14 · The source column includes fallback execution without a documented exact effort.
• 1 · The GLM card attributes this evaluation to Proximal; it is not a new Z.ai comparison. The source column includes fallback execution without a documented exact effort. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
• 1 · The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison. The source column includes fallback execution without a documented exact effort.
• 3 · Legacy self-report lacks a reviewed comparison configuration