Fable 5.1: score and benchmark evidence
Historical release · · Anthropic
131.2 points · Rank 2 among 19 ranked models · Stability range 123.3–138.1 points.
Rank follows the point estimate; it does not establish statistically significant superiority. The scale is anchored at mean 100, SD 15 in the frozen calibration cohort, not human IQ or a percentage.
One score summarizes demonstrated capability across published reasoning settings and seven equally weighted domains. Related benchmark variants share a family budget, and influence from one evaluator is capped.
Release tli-2026-v1.0-2026-09-06-presentation-1. Methodology and limitations for this release.
This page preserves historical evidence. See the current model record.
Capability domains
Domain scores use calibration-cohort standard-deviation units. Unmeasured domains are shown as unavailable, not zero.
| Domain | Score (SD units) | Observed benchmarks |
|---|---|---|
| Knowledge & reasoning | 1.09 | 7 |
| Coding & software engineering | 1.14 | 11 |
| Agentic tool & computer use | 0.63 | 3 |
| Professional & real-world work | 0.87 | 10 |
| Multimodal & vision | 0.62 | 3 |
| Cybersecurity | Unavailable | 0 |
| Preference & communication | 0.85 | 1 |
Published benchmark evidence
35 results contribute to this score, from 61 collected results and 33 contributing benchmark families. Counts are not independent sample sizes.
Results, source citations, review decisions and compatible reasoning modes are stored in a versioned relational database. Each publication uses a sealed, checksum-verified export; CSV files are optional exports, not editable scoring inputs. Previous revisions remain available for audit. Collected means a numeric result exists in the database. Used means its source, exact model checkpoint and benchmark protocol have been reviewed and its benchmark has a frozen calibration supported by multiple providers. For each benchmark we select the highest published aggregate across comparable reasoning modes, not necessarily maximum effort, and count it once. More tested settings provide more chances to record a high score; this selection advantage is not corrected by the conditional interval. Developer-reported and sole/unspecified settings remain eligible and disclosed. Unresolved does not mean false or useless: conflicting metrics, unverified citations and unmatched versions stay collected until reconciled.
The score stability range is a 95% bootstrap score interval conditional on frozen calibration and comparable evidence availability. It resamples benchmark families and evaluators and adds a frozen missing-evidence correction. It excludes selection across reasoning settings, selective publication, calibration changes and new domains. It is not a 95% guarantee about true capability or where a future score will land. Sparse or conflicting evidence can widen the range.
Reporting sensitivity: ±1.4 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1853 native-points
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
Terminal-Bench 2.1: 91.4%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
DeepSWE v1.1: 67.4%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Fable 5.1 final snapshot; adaptive max; five trials
Metric: mean pass rate, 113 DeepSWE v1.1 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LMArena (Chatbot Arena) — Text: 1504.213301 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5.1-max; Arena text overall; style control enabled
Metric: style-controlled text overall Elo
Original source · Retrieved 2026-09-06
Best published reasoning-mode rating within the same text overall board. Different leaderboard slices and undated earlier DeepSeek checkpoints are not pooled.
AA Intelligence Index v4.1.1 (score): 66 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 93.74%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
AA-LCR: 80%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
Current AA result is LCR v1.1. The inherited AA-LCR row has no reviewed version match; a new version cannot silently substantiate the older value.
Finance Agent v2 — Vals: 58.88%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: fabv2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Excel Modeling Benchmark — Vals: 76.67%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: emb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SciCode: 62%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
Humanity's Last Exam (no tools): 60.9%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
Legal Research Bench — Vals: 55.29%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: legal_research overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Harvey LAB (Vals): 6.67%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: hlab overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Briefcase Overall Elo: 1694 native-points
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
MedScribe — Vals: 91.29%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: medscribe overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LegalBench — Vals: 88.51%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: legal_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
TaxEval v2 — Vals: 75.96%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: tax_eval_v2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Public Benefits Bench — Vals: 74.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: public-benefits-bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MedCode — Vals: 53.51%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: medcode overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Omniscience: 43 native-points
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
MMLU Pro — Vals: 92.38%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: mmlu_pro overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveBench: 83.414155%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5-1-max-effort; LiveBench 2026-06-25 release
Metric: official overall: equal mean of seven category means
Original source · Retrieved 2026-09-06
Task mapping archived from categories_2026_06_25.json. Aggregate follows the official UI, not a flat mean of the 23 tasks. Undated old DeepSeek checkpoints excluded.
MortgageTax — Vals: 70.79%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: mortgage_tax overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SAGE — Vals: 48.53%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: sage overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Toolathlon-Verified: 77.8%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 77.8 for Fable 5.1 on Toolathlon-Verified still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
LiveCodeBench: 90.52%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: lcb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Humanity's Last Exam w/ tools: 65%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Fable 5.1; OpenAI comparison table; maximum across reasoning modes
Metric: Humanity's Last Exam (w/ tools)
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ProgramBench v1 (Raw Pass Rate) — Vals: 82.688%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: anthropic/claude-fable-5-1 · compute=max
Metric: Raw Pass Rate: mean percent of hidden behavioral tests passed per task. Not Fully Resolved (all tests pass) and not Almost Resolved (≥95% of tests pass).
Original source · Retrieved 2026-09-05
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
FrontierSWE: 57%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 57 for Fable 5.1 on FrontierSWE still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierMath v2 Tier 4: 87.804878%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5-1_max; task version 2.0.0
Metric: mean score percentage, FrontierMath-Tier-4-v2-Private
Original source · Retrieved 2026-09-06
Exact Epoch task version; selected best mean score across reported reasoning configurations. No pooling of task versions or substitution of best scorer output.
CursorBench v3.2: 73.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Fable 5.1 Max; Cursor harness
Metric: CursorBench 3.2 score percentage
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
APEX-Agents Mean Criteria Passed: 62%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5.1; max; loop_truncated_tools_agent
Metric: mean-score
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SWE-bench Pro: 81.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 81.2 for Fable 5.1 on SWE-bench Pro still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
APEX-SWE (Pass@1, Terminus-2): 63.6%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5.1; max; terminus-2
Metric: pass-1
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MMMU-Pro: 90.64%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
ARC-AGI-2: 90%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Fable 5.1; XHigh; ARC Prize standard harness
Metric: semi-private verified score percentage
Original source · Retrieved 2026-09-06
Best reasoning variant within the verified standard-harness summary. Provider Adapter, public tasks and community agent scores are not substituted.
OSWorld 2.0 — Anthropic H2H: 77.9%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 77.9 for Fable 5.1 on OSWorld 2.0 — Anthropic H2H still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierCode v1.1 Extended: 63.6%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Claude Fable 5.1; medium; claude-code
Metric: v1.1 Extended cost-adjusted new_score, 150 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MathArena — ArXivMath Jun 2026: 91.3%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 91.3 for Fable 5.1 on MathArena — ArXivMath Jun 2026 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
OfficeQA Pro †: 69%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 69 for Fable 5.1 on OfficeQA Pro † still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierCode v1.1 Main — Anthropic H2H: 50.9%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 50.9 for Fable 5.1 on FrontierCode v1.1 Main — Anthropic H2H still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
AutomationBench — Anthropic H2H: 31.4%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 31.4 for Fable 5.1 on AutomationBench — Anthropic H2H still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Harvey Legal Agent Benchmark — held-out: 16.7%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 16.7 for Fable 5.1 on Harvey Legal Agent Benchmark — held-out still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
τ³-Banking: 47.2%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
CritPt: 29.7%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Original source · Retrieved 2026-09-06
AA labels this configuration Default Fallback; per-evaluation fallback use is not established. Do not attribute a multi-model result to the named model alone.
Terminal-Bench 4.0: 57.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Fable 5.1; max; Claude Code
Metric: resolution rate, v4.0.0 66 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ProofBench v1.1 — Vals: 100%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: proof_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Vibe Code Bench v1.1 — Vals: 90.26%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: anthropic_claude-fable-5-1; Vals max effort
Metric: vibe-code overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MineBench: 2050 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Unresolved Pro/base model identities in source catalog; exclude until matched.
ARC-AGI-1: 97.5%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Fable 5.1; Max; ARC Prize standard harness
Metric: semi-private verified score percentage
Original source · Retrieved 2026-09-06
Best reasoning variant within the verified standard-harness summary. Provider Adapter, public tasks and community agent scores are not substituted.
BenchCAD (Vision2Code subset): 84.3%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: Fable 5.1; max; with tools; 1000-file subset; three disclosed reference modifications
Metric: mean voxel IoU multiplied by 100
Original source · Retrieved 2026-09-06
Matched 1000-file Vision2Code subset and disclosed modified grading. Full-set OpenAI results cannot be silently compared as this subset.
Terminal-Bench Science 0.1: 52.6%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Fable 5.1; publisher-reported maximum across reasoning efforts; OpenAI research/API evaluation
Metric: Terminal-Bench Science 0.1 as labelled in OpenAI comparison table
Original source · Retrieved 2026-09-06
Developer-reported maximum across reasoning modes. Exact selected mode is not individually disclosed. Research prompts/tools may differ from production; protocol-specific rows remain separate.
Harvey LAB-AA: 93.02%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 93.02 for Fable 5.1 on Harvey LAB-AA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Vending-Bench 2: 5421.556667 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Claude Fable 5.1; Andon Labs Vending-Bench 2
Metric: arithmetic mean final bank balance USD after one simulated year
Original source · Retrieved 2026-09-06
Compare reasoning configurations using their mean over runs. Geometric mean, individual best runs, Fireworks Kimi endpoint, Vending Arena, and April DeepSeek Pro are not substituted.
Internal Database Migration Tasks — OpenAI: 57.8%
Contributes to the score. Developer-reported. Review status: reviewed-developer.
Configuration: Fable 5.1; publisher-reported maximum across reasoning efforts; OpenAI research/API evaluation
Metric: Internal Database Migration Tasks — OpenAI as labelled in OpenAI comparison table
Original source · Retrieved 2026-09-06
Developer-reported maximum across reasoning modes. Exact selected mode is not individually disclosed. Research prompts/tools may differ from production; protocol-specific rows remain separate.
Mystery Game Puzzles v1.0.4 — Epoch: 58%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5-1_max; task version 1.0.4
Metric: mean score percentage, Mystery Game Puzzles
Original source · Retrieved 2026-09-06
Exact Epoch task version; selected best mean score across reported reasoning configurations. No pooling of task versions or substitution of best scorer output.
FrontierMath Erdos (68 conjectures) — Epoch: 0 native-points
Not used in the score. Source category: independent. Review status: reviewed-independent.
Configuration: claude-fable-5-1_max; task version
Metric: mean score percentage, FrontierMath-Erdos
Original source · Retrieved 2026-09-06
Exact Epoch task version; selected best mean score across reported reasoning configurations. No pooling of task versions or substitution of best scorer output.
RuneBench (30m, mean ln(1 + XP/min)): 6.143277 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: fable51-xhigh
Metric: Arithmetic mean of ln(1 + peakXpRate) over all 16 skills, exactly as the owner’s Heatmap.js default ranking. Data rates are already normalized; do not divide by 200 again.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
VoxelBench (text-to-voxel, Glicko-2): 2245 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: Claude Fable 5.1
Metric: Glicko-2 rating from the text-to-voxel board; not win percentage, deviation, image-input mode or MineBench Elo.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Roboflow Vision Evals (six-task mean, high tier): 82.516667%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: Require a complete six-task high-tier panel, the highest published benchmark tier. Retain high-tier scores even when lower than low-tier. Do not substitute the best of three repetitions: use the published mean. Each panel enters the fit once; do not also fit its components.
Metric: Arithmetic mean of six published high-tier task means; derived by The Latent, not Roboflow’s official low-tier overall score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Code Arena WebDev (overall): 1762 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: claude-fable-5.1-max
Metric: Published overall WebDev preference rating, not task success percentage or Arena Text score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Cite this model record
The Latent. “Fable 5.1: score and benchmark evidence.” 2026-09-06. Release tli-2026-v1.0-2026-09-06-presentation-1.
Download release data and definitions (JSON) · Data usage terms
Related reporting
These dated stories provide reporting context; they may describe an earlier release.