RankingEffort benchmarks

Claude Fable 5.1 effort benchmarks

Compare measured Low, Medium, High and other settings. Every number keeps its source.

Model

Claude Fable 5.1

135 measured results · 5 reported effort labels · 63 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Claude Fable 5.1 · Max: 85.8 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Anthropic · 24.8% direct comparison weight · provider report
Cognition · 11.4% direct comparison weight · independent
LiveBench · 11.0% direct comparison weight · independent
Epoch AI · 11.0% direct comparison weight · independent
Terminal-Bench · 10.9% direct comparison weight · independent
Vals AI · 10.8% direct comparison weight · independent
ARC Prize · 10.3% direct comparison weight · independent
Artificial Analysis · 9.8% direct comparison weight · independent

These shares describe the comparisons entering the fit, not fractions of the final score.

How sensitive is this score?

Remove one evaluator or family and refit the graph against the same overall panel. Values use the matching dataset audited 2026-09-12. These are sensitivity checks, not confidence intervals; ranking eligibility may also change.

Removed evidence	Recomputed score	Change
Artificial Analysis	85.8	-0.0
ARC Prize	86.2	+0.4
Datacurve	84.1	-1.7
LiveCodeBench	85.8	-0.0
Scale	86.1	+0.3
Terminal-Bench	83.3	-2.4
Cognition	86.7	+0.9
LiveBench	87.9	+2.1
SWE-rebench	85.6	-0.2
Epoch AI	86.5	+0.8
Vals AI	85.2	-0.5
Provider reports · Anthropic	79.0	-6.7
Provider reports · Moonshot AI	85.7	-0.1
Provider reports · Meta	85.7	-0.1
Provider reports · Mistral	85.8	+0.0
All provider reports	78.8	-6.9

Every benchmark family

Removed evidence	Recomputed score	Change
terminal-bench	83.4	-2.4
deepswe	84.1	-1.6
frontiercode	86.7	+0.9
harvey	86.4	+0.6
livebench-data	86.2	+0.5
livebench-instructions	86.2	+0.4
arc-agi	86.1	+0.4
multi-swe-bench	85.4	-0.3
livebench-coding	85.4	-0.3
mmmu-pro	86.1	+0.3
vals-legal-research	85.5	-0.3
vals-excel-modeling	85.5	-0.3
livebench-math	85.5	-0.3
gpqa	86.0	+0.2
frontiermath	85.5	-0.2
swe-rebench	85.6	-0.2
arc-agi-3	85.6	-0.2
simpleqa	85.9	+0.2
vibe-code	85.6	-0.2
aime	85.6	-0.1
swe-atlas-test-writing	85.6	-0.1
vals-finance-agent	85.9	+0.1
swe-atlas-qna	85.6	-0.1
gdp-pdf	85.9	+0.1
tau-bench	85.7	-0.1
ifbench	85.7	-0.1
vals-code-migration	85.7	-0.1
critpt	85.8	+0.1
omniscience	85.8	+0.1
mmlu-pro	85.7	-0.1
analyst-agent	85.7	-0.1
epoch-game-puzzles	85.8	+0.1
aa-lcr	85.7	-0.0
briefcase	85.7	-0.0
hle	85.8	+0.0
enigma-eval	85.8	+0.0
scicode	85.8	+0.0
itbench	85.8	-0.0
apex-agents	85.8	+0.0
automationbench	85.8	+0.0
swe-atlas-refactoring	85.8	-0.0
gdpval	85.8	-0.0
enterprise-ops	85.8	-0.0
livecodebench	85.8	+0.0
math500	85.8	+0.0
gmmlu	85.8	+0.0
livebench-language	85.8	+0.0
livebench-reasoning	85.8	+0.0
swe-bench-pro	85.8	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 203 observations, 134 contributing, 2 matched without graph weight and 67 excluded. Counts do not establish rank eligibility.

5 · Benchmark family or source protocol has not been reviewed
2 · Starred protocol annotation requires row-specific review before ranking.
4 · No matched, identified effort unit; duplicates and unnamed comparators do not add evidence
2 · No matched opponent in this evaluation unit
29 · Supporting evidence outside the reviewed capability core
16 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
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.
4 · System card section8.15.5 confirms11of324trials were partly or fully completed by Opus4.8fallback; actual mixed-model execution, not merely available fallback.
4 · Legacy self-report lacks a reviewed comparison configuration

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AClaude Fable 5.1 · Max4 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A79.6Supported
Hard reasoning
A76.4Supported
Coding
A89.7Supported
Human pref
Unknown
Knowledge
A77.9Supported
Multimodal
Unknown
Long context
A85.7Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Compare this configuration →Explore the model evidence profile →

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	Low	Medium	High	XHigh	Max
AA-AnalystAgentArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks solved on all 5 of 5 attempts · 80 tasks, 5 attempts per task · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	57.5% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	1,483.73 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	1,531.2 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	1,578.19 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	1,650.01 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	1,661.82 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	82.33% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	84.67% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	83.67% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	83% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	85.33% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	52.24% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	54.66% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	55.32% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	57.77% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	59.38% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	27.71% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	29.14% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	30.29% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	31.14% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	29.71% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
GDP.pdf: All-passArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	28% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	26.8% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	26.8% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	26.2% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	26.2% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
GDPval-AA v2 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-12.	1,503.72 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	1,579.31 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	1,649.77 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	1,745.29 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	1,763.64 Elo Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	88.08% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	88.59% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	90.61% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	93.43% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	93.74% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
Harvey LAB-AA: Criterion Pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of atomic pass/fail rubric criteria the deliverables satisfy, graded by a single LLM judge · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	92.33% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	92.65% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	92.95% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	93.27% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	93.02% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	48.89% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	53.8% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	55.93% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	58.71% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	59.13% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	71.11% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-09-12.	34.13 Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	37.6 Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	40.8 Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	42.38 Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	43.45 Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	60.23% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	63.1% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	64.93% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	66.22% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	67.23% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	56.71% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	56.37% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	58.68% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	60.88% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	63.08% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	38.97% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	41.03% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	43.09% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	45.77% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	47.22% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	85.02% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	88.01% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	89.89% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	91.01% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	91.39% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-12.	40.4% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-low	44.95% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-medium	52.02% Reported settings Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-high	55.05% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1-xhigh	52.02% Reported settings Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5-1
ARC-AGI-2ARC Prize · v2 Semi-Private Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	78.33% Reported settings Claude Fable 5.1 (Low); Source model ID: anthropic-claude-fable-5-1-low; 120 tasks	86.25% Reported settings Claude Fable 5.1 (Medium); Source model ID: anthropic-claude-fable-5-1-medium; 120 tasks	88.75% Reported settings Claude Fable 5.1 (High); Source model ID: anthropic-claude-fable-5-1-high; 120 tasks	90% Reported settings Claude Fable 5.1 (XHigh); Source model ID: anthropic-claude-fable-5-1-xhigh; 120 tasks	90% Reported settings Claude Fable 5.1 (Max); Source model ID: anthropic-claude-fable-5-1-max; 120 tasks
FrontierCode 1.1 · extended-claude-codeCognition · claude-code Benchmark details FrontierCode 1.1; claude-code. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	61.62% Reported settings FrontierCode 1.1; extended; 150 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	63.6% Reported settings FrontierCode 1.1; extended; 150 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	62.68% Reported settings FrontierCode 1.1; extended; 150 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	61.35% Reported settings FrontierCode 1.1; extended; 150 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	62.03% Reported settings FrontierCode 1.1; extended; 150 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0
FrontierCode 1.1 · main-claude-codeCognition · claude-code Benchmark details FrontierCode 1.1; claude-code. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	49.82% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort low; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	50.91% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	50.34% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort high; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	48.73% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort xhigh; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	50.28% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort max; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0
Terminal-Bench 4.0 · claudecodeTerminal-Bench · Claude Code Benchmark details Terminal-Bench 4.0; Claude Code. Open each result for its exact effort, task subset, metric and protocol details. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	57.9% Reported settings Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.8 percentage points, confidence level unspecified; release date 2026-09-01; board checked 2026-09-07
HLE · text only · Scale official evaluationScale · Scale official evaluation Benchmark details Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	46.8% Reported settings Scale text-only public HLE subset; shares the full HLE family budget; automatic answer judging.; published row 2026-09-03T18:19:45.000Z; reported margin ±2.1 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.	Not reported
HLE · full · Scale official evaluationScale · Scale official evaluation Benchmark details Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	46.5% Reported settings Scale full public HLE; 2,500 questions; automatic answer judging; temperature 0 when configurable. Public-set contamination caveats retained per result.; published row 2026-09-03T18:22:21.000Z; reported margin ±2 percentage points; Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions.	Not reported
SWE Atlas · QnA · claude codeScale · claude code Benchmark details 124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	59.95% Reported settings 124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-03-02T20:57:11.000Z; reported margin ±4.85 percentage points; No contamination annotation reported (not proof of absence) Starred protocol annotation requires row-specific review before ranking. Source label needs review	Not reported
SWE Atlas · Refactoring · claude codeScale · claude code Benchmark details 70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	56.67% Reported settings 70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-09-02T21:52:32.000Z; reported margin ±6.52 percentage points; No contamination annotation reported (not proof of absence)	Not reported
SWE Atlas · Test Writing · claude codeScale · claude code Benchmark details 90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	67.04% Reported settings 90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-09-02T19:02:52.000Z; reported margin ±5.33 percentage points; No contamination annotation reported (not proof of absence) Starred protocol annotation requires row-specific review before ranking. Source label needs review	Not reported
LiveBench · AMPS Hard · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	99% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · code completion · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	82.61% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · code generation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.14% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · connections · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	99.33% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · consecutive events · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.56% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · integrals with game · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	99% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · javascript · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	68.18% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · logic with navigation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	86% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · math comp · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	97.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · olympiad · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	92.97% Reported settings LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · paraphrase · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	71.52% Reported settings LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · plot unscrambling · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	75.17% Reported settings LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · python · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	70% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · simplify · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	70.17% Reported settings LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · spatial · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	100% Reported settings LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · story generation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	78.1% Reported settings LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · summarize · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	72.17% Reported settings LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · tablejoin · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	56.15% Reported settings LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · tablereformat · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	94.12% Reported settings LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · theory of mind · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	80.77% Reported settings LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · typescript · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	60% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · typos · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	94% Reported settings LiveBench official task evaluation; livebench-2026-06-25-typos; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
LiveBench · zebra puzzle · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	100% Reported settings LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-fable-5-1-max-effort; checkpoint=claude-fable-5-1
Epoch · Chess Puzzles · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	47% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5-1_max; run=EEGf5SDiF8jXB6NX7eR6Sa; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tier 4 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	87.8% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5-1_max; run=T56N3X4KLA3xz7tf5aCMGb; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tiers 1–3 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.18% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5-1_max; run=g7dXwZH2tWvqLg3X5idGs2; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionEpoch AI · Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	58% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-fable-5-1_max; run=dBHxnnTzLGz3nHis5LET6t; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	100% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5-1_max; run=mRAASXsUuoJmc2oR5G89zR; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · SimpleQA Verified · v1.2.0Epoch AI · Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	70.8% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-fable-5-1_max; run=ExyL3GN8s34tizrXV3VmS3; mean accuracy; https://epoch.ai/data/benchmarks.csv
Vals AI · Finance Agent v2Vals AI · Vals FAB v2 shared six-tool harness; two-hour task limit Benchmark details Overall weighted rubric accuracy, averaged over three runs on 450 tasks. Dealbreaker failures and timeouts score zero. Related categories and all-pass scores are not additional votes. Three-model judge panel; private test set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	58.88% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}
Vals AI · Code Migration v1Vals AI · Vals Code Migration shared agent harness Benchmark details Hidden behavior-test pass rate, equally weighted across 40 repositories (30 CLI and 10 COBOL-to-Java). Anti-cheat failures score zero. Code-quality ratings and language splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	54.61% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}
Vals AI · Legal Research Bench v1Vals AI · Vals Legal Research shared five-tool harness; three-hour task limit Benchmark details All-pass accuracy on 208 private legal research tasks. Every expert rubric check must pass; GPT-5.4 judges responses. Partial-credit scores and practice-area splits are not additional votes. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	55.29% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}
Vals AI · Excel Modeling Benchmark v1Vals AI · Vals EMB shared workbook agent harness; 3.5-hour task limit Benchmark details Mean of seven equally weighted task categories. Template submissions use recalculated Excel cell accuracy; scratch submissions use rubric checks judged by GPT-5.4 Mini XHigh. Partial credit does not mean task completion. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	76.67% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}
Vals AI · MMLU-Pro v1Vals AI · Vals MMLU-Pro five-shot chain-of-thought; regex answer grading Benchmark details Mean accuracy across 14 subjects under Vals five-shot prompting. Subject splits share one family and are not additional votes. Vals labels this benchmark archived; it is historical corroboration, not ongoing frontier evaluation. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	92.38% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-01","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}
Vals AI · Terminal-Bench 2.1Vals AI · Vals Terminus 2 harness; pass@1 on 89 tasks Benchmark details Overall task pass rate under the shared Terminus 2 configuration. All task tests must pass. Difficulty splits share one family. Fable 5 and Opus 5 mixed-checkpoint fallback runs are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	85.02% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"high","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}	Not reported	Not reported
Vals AI · Vibe Code Bench v1.1Vals AI · Vals modified OpenHands harness; five hours or 1,000 turns per app Benchmark details Mean app test pass rate on the canonical v1.1 test set. Browser Use executes workflow tests; each test requires at least 90% of its substeps. Automated judging can introduce error. Alternate agents are excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	90.26% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":"OpenHands"}
Vals AI · Harvey Legal Agent Benchmark v1Vals AI · Vals Harvey held-out legal file-work protocol; internet disabled Benchmark details Mean task resolution across two judges (GPT-5.5 Medium and Sonnet 4.6), requiring every criterion to pass. Criteria pass rates and practice-area splits do not add votes. Shared Harvey family; Fable 5 fallback run excluded. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	Not reported	6.67% Reported settings {"checkpoint":"claude-fable-5-1","evaluatorModel":"anthropic/claude-fable-5-1","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":"max","reasoning":null,"temperature":1,"top_p":null,"max_output_tokens":128000,"verbosity":null,"provider":"Anthropic","harness":null}

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 7,424 results across 240 models · Collected 2026-09-12

Claude Fable 5.1 effort benchmarks

Claude Fable 5.1

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context