RankingEffort benchmarks

Claude Sonnet 5 effort benchmarks

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

Model

Claude Sonnet 5

135 measured results · 7 reported effort labels · 64 benchmark/harness combinations. Model evidence and sources →

Capability score evidence

Claude Sonnet 5 · XHigh: 39.9 overall comparison score. Meets the overall evidence requirements.

Which sources carry the weight?

Cognition · 25.8% direct comparison weight · independent
LiveBench · 22.6% direct comparison weight · independent
Epoch AI · 20.5% direct comparison weight · independent
Artificial Analysis · 17.4% direct comparison weight · independent
Datacurve · 13.7% 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	40.3	+0.4
ARC Prize	41.0	+1.1
Datacurve	38.7	-1.2
LiveCodeBench	39.9	-0.0
Scale	41.1	+1.1
Terminal-Bench	39.7	-0.2
Cognition	37.3	-2.6
LiveBench	40.7	+0.8
SWE-rebench	39.4	-0.5
Epoch AI	43.4	+3.5
Vals AI	38.9	-1.1
Provider reports · Anthropic	39.9	-0.0
Provider reports · Moonshot AI	39.9	-0.0
Provider reports · Meta	39.9	-0.0
Provider reports · Mistral	39.9	+0.0
All provider reports	39.9	-0.1

Every benchmark family

Removed evidence	Recomputed score	Change
frontiercode	37.3	-2.6
simpleqa	41.9	+1.9
multi-swe-bench	38.5	-1.4
livebench-instructions	41.3	+1.3
deepswe	38.8	-1.2
livebench-language	41.0	+1.1
arc-agi	41.0	+1.0
mmmu-pro	40.9	+1.0
livebench-coding	39.0	-1.0
livebench-data	40.7	+0.8
livebench-reasoning	39.2	-0.7
aime	39.3	-0.6
gpqa	39.4	-0.6
hle	40.5	+0.5
epoch-game-puzzles	39.4	-0.5
swe-rebench	39.4	-0.5
mmlu-pro	40.3	+0.4
swe-atlas-qna	39.7	-0.3
gdp-pdf	40.2	+0.2
omniscience	40.1	+0.2
tau-bench	39.7	-0.2
ifbench	39.7	-0.2
harvey	39.8	-0.2
swe-atlas-test-writing	39.8	-0.2
enterprise-ops	39.8	-0.1
vals-finance-agent	39.8	-0.1
frontiermath	39.8	-0.1
vibe-code	39.8	-0.1
arc-agi-3	39.8	-0.1
aa-lcr	40.0	+0.1
briefcase	39.8	-0.1
terminal-bench	39.8	-0.1
enigma-eval	40.0	+0.1
livebench-math	39.9	-0.1
apex-agents	40.0	+0.1
automationbench	40.0	+0.1
vals-legal-research	39.9	-0.1
vals-excel-modeling	39.9	-0.0
gdpval	39.9	-0.0
itbench	39.9	-0.0
scicode	39.9	-0.0
critpt	40.0	+0.0
swe-atlas-refactoring	39.9	-0.0
livecodebench	39.9	-0.0
analyst-agent	40.0	+0.0
gmmlu	39.9	+0.0
vals-code-migration	39.9	-0.0
swe-bench-pro	39.9	+0.0
math500	39.9	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 150 observations, 128 contributing, 0 matched without graph weight and 22 excluded. Counts do not establish rank eligibility.

6 · Benchmark family or source protocol has not been reviewed
1 · Effort is not identified
6 · Supporting evidence outside the reviewed capability core
8 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
1 · Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit.

Inspect every observation and exclusion →

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AClaude Sonnet 5 · XHigh4 of 7 capabilities supported

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

Agentic
A36.2Supported
Hard reasoning
A50.4Supported
Coding
A54.4Supported
Human pref
Unknown
Knowledge
A18.0Supported
Multimodal
Unknown
Long context
A37.3Preliminary

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	Non-reasoning	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	46.25% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	927.41 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	1,053.88 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	1,177.84 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	1,273.41 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	1,355.19 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	67.33% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	73.67% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	76.67% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	76.67% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	82% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	70% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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.	19.9% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	27.87% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	32.1% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	34.48% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	36.51% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	4.57% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	8.57% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	15.14% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	15.43% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	16.86% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	1.14% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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	43.87% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	44.67% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	9.4% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	11.6% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	9.4% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	12.6% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	13.2% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	1,145.04 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	1,222.52 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	1,308.45 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	1,400.77 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	1,500.86 Elo Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	1,283.47 Elo Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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	91.11% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	80% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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	90.07% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	21.92% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	29.98% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	35.73% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	39.02% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	41.29% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	19.05% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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	55% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	Not reported
MMMU-ProArtificial 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	77.28% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	71.91% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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.	-8.23 Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	-6.87 Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	-3.68 Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	3.18 Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	16.45 Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	-0.65 Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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.	37.35% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	37.1% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	37.43% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	38.97% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	40.05% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	33.8% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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.	50.12% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	51.62% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	54.28% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	54.05% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	54.28% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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	37.32% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	15.67% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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	80.52% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	75.28% Reported settings Claude Sonnet 5 (Non-reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning	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.	2.53% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Low Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-low	2.02% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Medium Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-medium	5.05% Reported settings Claude Sonnet 5 (Adaptive Reasoning, High Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-high	7.07% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-xhigh	14.14% Reported settings Claude Sonnet 5 (Adaptive Reasoning, Max Effort); Model source: https://artificialanalysis.ai/models/claude-sonnet-5	Not reported	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.	30.5% Reported settings claude-sonnet-5; Reported effort: low; 113 unique tasks; 449 attempts; 4 runs	39.8% Reported settings claude-sonnet-5; Reported effort: medium; 113 unique tasks; 450 attempts; 4 runs	48.2% Reported settings claude-sonnet-5; Reported effort: high; 113 unique tasks; 452 attempts; 4 runs	49.7% Reported settings claude-sonnet-5; Reported effort: xhigh; 113 unique tasks; 451 attempts; 4 runs	53.8% Reported settings claude-sonnet-5; Reported effort: max; 113 unique tasks; 442 attempts; 4 runs	Not reported	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	74.61% Reported settings Sonnet 5; Reported effort: high; 445 trials; recorded 2026-06-30	Not reported	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.	44.46% 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 0.0007	49.28% 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	52.71% 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	56.18% 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 0.006	54.85% 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 0.0053	Not reported	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.	28.71% 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 0.001	35.2% 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	39.35% 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	42.73% 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 0.005	42.36% 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 0.003	Not reported	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	12.4% Reported settings Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.1 percentage points, confidence level unspecified; release date 2026-06-30; board checked 2026-09-07	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	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	78.26% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	83.1% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	95.5% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	74.74% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	88% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	68.18% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	86% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	95.1% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	90.67% Reported settings LiveBench official task evaluation; livebench-2026-06-25-olympiad; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	61.25% Reported settings LiveBench official task evaluation; livebench-2026-06-25-paraphrase; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	53.41% Reported settings LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	60% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	60.65% Reported settings LiveBench official task evaluation; livebench-2026-06-25-simplify; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	100% Reported settings LiveBench official task evaluation; livebench-2026-06-25-spatial; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	62.32% Reported settings LiveBench official task evaluation; livebench-2026-06-25-story_generation; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	71.22% Reported settings LiveBench official task evaluation; livebench-2026-06-25-summarize; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	42.44% Reported settings LiveBench official task evaluation; livebench-2026-06-25-tablejoin; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	98.04% Reported settings LiveBench official task evaluation; livebench-2026-06-25-tablereformat; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	80.77% Reported settings LiveBench official task evaluation; livebench-2026-06-25-theory_of_mind; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	50% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-typescript; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	76% Reported settings LiveBench official task evaluation; livebench-2026-06-25-typos; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	88% Reported settings LiveBench official task evaluation; livebench-2026-06-25-zebra_puzzle; claude-sonnet-5-xhigh-effort; checkpoint=claude-sonnet-5	Not reported	Not reported	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	52.86% Reported settings SWE-rebench standardized ReAct tools; swe-rebench-2026-06-tools; Sonnet 5 [high]; checkpoint=claude-sonnet-5	Not reported	Not reported	Not reported	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.	Not reported	Not reported	Not reported	35% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_xhigh; run=DAyGUk5kLRdwNkSPZgqmos; mean accuracy; https://epoch.ai/data/benchmarks.csv	16% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_max; run=czNLsHc7tBqBWtWaoTSLXh; mean accuracy; https://epoch.ai/data/benchmarks.csv	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	29.27% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-5_max; run=bqiVinHXFcgyFGPstJwXJN; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	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	65.61% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=claude-sonnet-5_max; run=V6YuGpcu8MCbJNXKoJMA6b; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	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.	Not reported	Not reported	Not reported	90.53% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-5_xhigh; run=HhiYxEx3Bf8YDPUh34K4DC; mean accuracy; https://epoch.ai/data/benchmarks.csv	80.3% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=claude-sonnet-5_max; run=FNXAt76ZUS3sWhQDFMga7U; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	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	35% Reported settings Epoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=claude-sonnet-5_max; run=YdcyYXLzqfPUSSgGv4MTED; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported
Epoch · Mystery Game Puzzles · v1.0.4 · Exact moveEpoch AI · Epoch AI Inspect; task 1.0.4; scorer exact_match_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	Not reported	Not reported	16% Reported settings Epoch AI Inspect; task 1.0.4; scorer exact_match_next_move_scorer; model=claude-sonnet-5; run=AZHoMLTNQEcKLwtv7QzBLZ; 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	94.72% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_xhigh; run=T2wFfuSkUdyjpyqurxNmNK; mean accuracy; https://epoch.ai/data/benchmarks.csv	80% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=claude-sonnet-5_max; run=XRutLYUVUePe69APTSTw8S; mean accuracy; https://epoch.ai/data/benchmarks.csv	Not reported	Not reported
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	32.9% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-5_xhigh; run=Qw4tGw38pk4sdsEehhrLSR; mean accuracy; https://epoch.ai/data/benchmarks.csv	33.7% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=claude-sonnet-5_max; run=LPo74T9L3CawnKX5LLUrSZ; 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	53.91% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	44.39% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	41.83% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	66.32% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	87.55% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	74.53% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	81.33% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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	5% Reported settings {"checkpoint":"claude-sonnet-5","evaluatorModel":"anthropic/claude-sonnet-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	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 Sonnet 5 effort benchmarks

Claude Sonnet 5

Capability score evidence

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context