RankingEffort benchmarks

Claude Fable 5 effort benchmarks

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

Model

Claude Fable 5

93 measured results · 6 reported effort labels · 73 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Claude Fable 5 · High: 74.0 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Cognition · 17.6% direct comparison weight · independent
SWE-rebench · 16.7% direct comparison weight · independent
ARC Prize · 15.9% direct comparison weight · independent
Epoch AI · 13.7% direct comparison weight · independent
Scale · 13.5% direct comparison weight · independent
Terminal-Bench · 12.1% direct comparison weight · independent
Datacurve · 10.5% 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	73.2	-0.8
ARC Prize	75.2	+1.3
Datacurve	73.1	-0.9
LiveCodeBench	74.0	+0.0
Scale	70.9	-3.1
Terminal-Bench	72.9	-1.1
Cognition	71.6	-2.4
LiveBench	74.2	+0.2
SWE-rebench	77.9	+3.9
Epoch AI	78.1	+4.1
Vals AI	73.4	-0.5
Provider reports · Anthropic	73.9	-0.1
Provider reports · Moonshot AI	74.1	+0.1
Provider reports · Meta	74.0	+0.0
Provider reports · Mistral	74.0	+0.0
All provider reports	74.0	+0.0

Every benchmark family

Removed evidence	Recomputed score	Change
swe-rebench	77.9	+3.9
enigma-eval	70.6	-3.4
frontiercode	71.6	-2.4
gpqa	75.9	+1.9
arc-agi	75.6	+1.6
aime	72.8	-1.1
terminal-bench	72.9	-1.1
deepswe	73.1	-0.9
epoch-game-puzzles	73.5	-0.4
mmmu-pro	74.3	+0.3
arc-agi-3	73.6	-0.3
hle	74.2	+0.2
frontiermath	73.8	-0.2
swe-atlas-test-writing	74.1	+0.2
tau-bench	73.8	-0.1
swe-atlas-qna	73.8	-0.1
ifbench	73.8	-0.1
mmlu-pro	74.1	+0.1
livebench-instructions	74.1	+0.1
critpt	74.1	+0.1
simpleqa	74.0	+0.1
multi-swe-bench	73.9	-0.1
livebench-coding	73.9	-0.1
gdp-pdf	74.0	+0.1
livebench-data	74.0	+0.1
harvey	73.9	-0.1
scicode	74.0	+0.1
livebench-reasoning	73.9	-0.0
livebench-language	74.0	+0.0
swe-atlas-refactoring	73.9	-0.0
vals-legal-research	73.9	-0.0
itbench	73.9	-0.0
vals-excel-modeling	73.9	-0.0
apex-agents	74.0	+0.0
briefcase	73.9	-0.0
vals-finance-agent	73.9	-0.0
vibe-code	73.9	-0.0
vals-code-migration	73.9	-0.0
omniscience	74.0	+0.0
automationbench	74.0	+0.0
gmmlu	74.0	+0.0
livecodebench	74.0	+0.0
enterprise-ops	73.9	-0.0
gdpval	73.9	-0.0
analyst-agent	73.9	-0.0
aa-lcr	74.0	+0.0
math500	74.0	+0.0
swe-bench-pro	74.0	-0.0
livebench-math	74.0	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 272 observations, 94 contributing, 2 matched without graph weight and 176 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
1 · Fewer than two distinct model identities remain in this evaluation
2 · Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking
36 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
89 · Supporting evidence outside the reviewed capability core
1 · 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.
6 · 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
3 · 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, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison.
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 Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison.
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.
7 · The source states that Fable 5 results may involve fallback execution; an exact configuration is not established.
6 · The source column includes fallback execution without a documented exact effort.
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

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AClaude Fable 5 · High2 of 7 capabilities supported

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

Agentic
Unknown
Hard reasoning
A76.2Supported
Coding
A77.7Supported
Human pref
Unknown
Knowledge
Unknown
Multimodal
Unknown
Long context
Unknown

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	Unspecified
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	48.75% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	1,529.62 Elo Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	82.33% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	54.07% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	28.57% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
EnterpriseOps-Gym-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · 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	51.12% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	24% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	1,631.46 Elo Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	92.63% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	93.56% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	55.47% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
IFBenchArtificial 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.	Not reported	Not reported	Not reported	Not reported	63.47% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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	64.44% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	43.3 Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	65.35% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	61% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
𝜏²-Bench TelecomArtificial 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.	Not reported	Not reported	Not reported	Not reported	98.54% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	38.14% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
Terminal-Bench HardArtificial 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.	Not reported	Not reported	Not reported	Not reported	62.88% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	84.64% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	Not reported	Not reported	Not reported	Not reported	42.42% Reported settings Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback); Model source: https://artificialanalysis.ai/models/claude-fable-5	Not reported
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.	76.81% Reported settings Claude Fable 5 (Low); Source model ID: anthropic-claude-fable-5-low; 120 tasks	82.5% Reported settings Claude Fable 5 (Medium); Source model ID: anthropic-claude-fable-5-medium; 120 tasks	87.5% Reported settings Claude Fable 5 (High); Source model ID: anthropic-claude-fable-5-high; 120 tasks	88.33% Reported settings Claude Fable 5 (XHigh); Source model ID: anthropic-claude-fable-5-xhigh; 120 tasks	89.17% Reported settings Claude Fable 5 (Max); Source model ID: anthropic-claude-fable-5-max; 120 tasks	Not reported
DeepSWE v1.1Datacurve · mini-swe-agent Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	59.6% Reported settings claude-fable-5; Reported effort: low; 113 unique tasks; 433 attempts; 4 runs	65.4% Reported settings claude-fable-5; Reported effort: medium; 113 unique tasks; 436 attempts; 4 runs	68.6% Reported settings claude-fable-5; Reported effort: high; 113 unique tasks; 430 attempts; 4 runs	69.9% Reported settings claude-fable-5; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs	69.7% Reported settings claude-fable-5; Reported effort: max; 113 unique tasks; 436 attempts; 4 runs	Not reported
Terminal-Bench 2.1Terminal-Bench · Claude Code Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	Not reported	83.82% Reported settings Fable 5; Reported effort: xhigh; 445 trials; recorded 2026-06-09	Not reported	Not reported
Terminal-Bench 2.1Terminal-Bench · Terminus 2 Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	80.45% Reported settings Fable 5; Reported effort: high; 445 trials; recorded 2026-06-09	Not reported	Not reported	Not reported
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.	60.8% 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	62.79% 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 0.002	64.25% 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 0.0013	64.94% 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 0.002	63.63% 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 0.0013	Not reported
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.	48.01% 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	49.82% 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 0.003	52.73% 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 0.002	53.48% 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 0.003	51.57% 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 0.002	Not reported
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	44.5% Reported settings Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.8 percentage points, confidence level unspecified; release date 2026-06-09; board checked 2026-09-07	Not reported
EnigmaEval · Scale official evaluationScale · Scale official evaluation Benchmark details Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	39.28% Reported settings Scale EnigmaEval puzzle-hunt accuracy; source-reported reasoning effort.; published row 2026-03-23T21:18:50.000Z; reported margin ±2.8 percentage points; No contamination annotation reported (not proof of absence)	Not reported	Not reported	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	39% 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 2026-03-02T20:20:06.000Z; reported margin ±5 percentage points; No contamination annotation reported (not proof of absence); Board footnote: elevated refusals on benign tasks are scored zero by the evaluator and remain in the published score.	Not reported	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	54.76% Reported settings 70 refactoring tasks across 10 repositories; behavior preservation and task-specific grading; source-reported agent harness.; published row 2026-06-11T17:55:16.000Z; reported margin ±6.76 percentage points; No contamination annotation reported (not proof of absence)	Not reported	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	55.6% 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 2026-06-11T17:41:27.000Z; reported margin ±5.8 percentage points; No contamination annotation reported (not proof of absence); Board footnote: elevated refusals on benign tasks are scored zero by the evaluator and remain in the published score.	Not reported	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-max-effort; checkpoint=claude-fable-5	Not reported
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	80.44% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	91.55% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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-max-effort; checkpoint=claude-fable-5	Not reported
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	91.36% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	97% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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-max-effort; checkpoint=claude-fable-5	Not reported
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	78% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	95.1% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	92.85% Reported settings LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	77.65% Reported settings LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	78.72% Reported settings LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	65% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	72.03% Reported settings LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	96% Reported settings LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	71.7% Reported settings LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	81.7% Reported settings LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	56.14% Reported settings LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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-max-effort; checkpoint=claude-fable-5	Not reported
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	84.62% Reported settings LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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	53.33% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-fable-5-max-effort; checkpoint=claude-fable-5	Not reported
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-max-effort; checkpoint=claude-fable-5	Not reported
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-max-effort; checkpoint=claude-fable-5	Not reported
SWE-rebench · 2026-06 · toolsSWE-rebench · SWE-rebench standardized ReAct tools Benchmark details Average resolved rate across repeated runs, not best-of-N success. Disjoint complete calendar months within each model’s tested range; standardized harness and all-language task set. Unit: percent. Source collected 2026-09-12.	Not reported	Not reported	57.62% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Fable 5 [high]; checkpoint=claude-fable-5	Not reported	Not reported	Not reported
Epoch · Chess Puzzles · v1.1.5Epoch AI · Epoch AI Inspect; task 1.1.5; 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	41% Reported settings Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match; model=claude-fable-5_max; run=bAR85KQmEATQP8j764jpBA; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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.	28% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_low; run=aftzew4ra4iax5D4R4vvfF; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	41% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_high; run=SoCkYbcxzkYHXqcqnEQwFN; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
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	90.2% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5_max; run=ReDAtJGGfRtrEGGWf4Zbsd; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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	87.02% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-fable-5_max; run=E28uZiJvrPgKtawbJpoZQ8; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
Epoch · GPQA diamond · v1.0.11Epoch AI · Epoch AI Inspect; task 1.0.11; scorer choice 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.	78.79% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_low; run=U5PsUdX2ak4kJ2hgnQkWnX; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	83.33% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_high; run=d23hYvSNGFo7rniLFyBWiu; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	85.86% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-fable-5_max; run=S5pm7ctk9zgPfbyHrbD9AV; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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	52% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-fable-5_max; run=X29V6KG3aVe5Nv5r3tsLHX; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
Epoch · OTIS Mock AIME 2024-2025 · v1.1.5Epoch AI · Epoch AI Inspect; task 1.1.5; 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	99.72% Reported settings Epoch AI Inspect; task 1.1.5; scorer model_extracted_exact_match; model=claude-fable-5_max; run=eiLEpRUvK48wUKDh4sYkzV; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported
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.	97.78% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_low; run=6E989Xxeuw925T7cCV3XGB; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	100% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-fable-5_high; run=hwrnvtEbDAocFtjcsHqsQh; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported	Not reported
Epoch · SimpleQA Verified · v1.0.0Epoch AI · Epoch AI Inspect; task 1.0.0; 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	70.7% Reported settings Epoch AI Inspect; task 1.0.0; scorer simpleqa_scorer; model=claude-fable-5_xhigh; run=SEnvgtunRa5GwAtU2sHa87; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported
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	56.31% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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}	Not reported
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	55.07% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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}	Not reported
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	49.52% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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}	Not reported
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	73.67% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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}	Not reported
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	91.5% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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}	Not reported
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	Not reported	Not reported	Not reported	80.52% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","sourceUpdatedOn":"2026-09-10","reasoning_effort":null,"compute_effort":null,"reasoning":null,"temperature":null,"top_p":null,"max_output_tokens":null,"verbosity":null,"provider":"Anthropic","harness":null} Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking Source label needs review
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	90.35% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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"}	Not reported
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	11.25% Reported settings {"checkpoint":"claude-fable-5","evaluatorModel":"anthropic/claude-fable-5","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} Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking Source label needs review	Not reported

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 effort benchmarks

Claude Fable 5

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context