RankingEffort benchmarks

Claude Sonnet 5.5

Compare models

129 measured results · 5 effort settings · 47 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AClaude Sonnet 5.5 · XHigh4 of 7 capabilities supported

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

Agentic
A65.7Supported
Hard reasoning
A62.2Supported
Coding
A81.9Supported
Human pref
Unknown
Knowledge
A48.2Supported
Multimodal
Unknown
Long context
A50.4Preliminary

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.

Capability score evidence

Claude Sonnet 5.5 · XHigh: 80.9 overall comparison score. Meets the overall evidence requirements.

5 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Shared-result disagreement. This aggregate order conflicts with matched benchmark results against 1 other configurations. Different test coverage and opponents affect the fit. Inspect published results before treating the rank as conclusive.

Which sources carry the weight?

Cognition · 48.2% direct comparison weight · independent of the model provider
Artificial Analysis · 29.7% direct comparison weight · independent of the model provider
LiveBench · 22.1% direct comparison weight · independent of the model provider

These shares describe the comparisons entering the fit, not fractions of the final score. Source balancing does not prove independence: overlapping sources may remain correlated.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-09-30.

Both ranks use the same surviving configurations for each removal. The cohort starts with 427 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	16 → 14	Up 2	192 remaining / 235 lost	83.1 (+2.1 points)
ARC Prize	16 → 15	Up 1	427 remaining / 0 lost	81.8 (+0.9 points)
Datacurve	16 → 15	Up 1	427 remaining / 0 lost	80.0 (-1.0 points)
LiveCodeBench	16 → 16	No movement	427 remaining / 0 lost	80.9 (-0.0 points)
Scale	16 → 15	Up 1	427 remaining / 0 lost	81.7 (+0.7 points)
Terminal-Bench	16 → 15	Up 1	427 remaining / 0 lost	80.7 (-0.2 points)
Cognition	16 → 38	Down 22	427 remaining / 0 lost	61.9 (-19.0 points)
LiveBench	16 → 8	Up 8	426 remaining / 1 lost	89.1 (+8.1 points)
SWE-rebench	16 → 17	Down 1	427 remaining / 0 lost	80.6 (-0.3 points)
Epoch AI	16 → 16	No movement	410 remaining / 17 lost	81.6 (+0.6 points)
Vals AI	16 → 17	Down 1	426 remaining / 1 lost	80.0 (-0.9 points)
Provider reports · Anthropic	16 → 16	No movement	427 remaining / 0 lost	80.8 (-0.1 points)
Provider reports · Moonshot AI	16 → 16	No movement	427 remaining / 0 lost	80.8 (-0.1 points)
Provider reports · Meta	16 → 16	No movement	427 remaining / 0 lost	80.8 (-0.2 points)
Provider reports · Mistral	16 → 16	No movement	427 remaining / 0 lost	80.9 (+0.0 points)
Provider reports · OpenAI	16 → 15	Up 1	427 remaining / 0 lost	80.7 (-0.2 points)
All provider reports	16 → 15	Up 1	427 remaining / 0 lost	80.3 (-0.7 points)

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

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

Every benchmark family

Removed evidence	Recomputed score	Change
frontiercode	61.9	-19.0
livebench-coding	79.0	-2.0
multi-swe-bench	82.3	+1.4
deepswe	80.0	-1.0
arc-agi	81.6	+0.7
livebench-math	80.3	-0.7
omniscience	81.4	+0.4
mmmu-pro	81.4	+0.4
aa-lcr	81.4	+0.4
arc-agi-3	80.6	-0.4
gdp-pdf	81.3	+0.4
livebench-language	81.3	+0.4
enigma-eval	81.3	+0.3
livebench-instructions	81.3	+0.3
ifbench	80.6	-0.3
swe-rebench	80.6	-0.3
livebench-data	81.2	+0.3
swe-atlas-test-writing	80.7	-0.3
hle	81.2	+0.3
briefcase	80.7	-0.3
terminal-bench-science	80.7	-0.3
tau-bench	80.7	-0.2
aime	80.7	-0.2
livebench-reasoning	81.2	+0.2
terminal-bench	80.8	-0.2
critpt	81.1	+0.2
gpqa	81.1	+0.1
itbench	81.1	+0.1
swe-atlas-qna	80.8	-0.1
mmlu-pro	81.0	+0.1
swe-atlas-refactoring	80.8	-0.1
vibe-code	80.8	-0.1
frontiermath	80.9	-0.1
livecodebench	80.9	-0.1
simpleqa	80.9	-0.1
vals-tax-agent	80.9	-0.0
gdpval	80.9	-0.0
vals-legal-research	80.9	-0.0
epoch-game-puzzles	81.0	+0.0
apex-agents	81.0	+0.0
gmmlu	80.9	-0.0
vals-excel-modeling	80.9	-0.0
math500	80.9	-0.0
vals-code-migration	81.0	+0.0
automationbench	80.9	-0.0
harvey	81.0	+0.0
analyst-agent	80.9	-0.0
swe-bench-pro	80.9	+0.0
vals-finance-agent	80.9	-0.0
enterprise-ops	80.9	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 131 observations, 119 contributing, 0 matched without graph weight and 12 excluded. Counts do not establish rank eligibility.

5 · Benchmark family or source protocol has not been reviewed
5 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
2 · Supporting evidence outside the reviewed capability core

Inspect every observation and exclusion →

Benchmark results

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

Benchmark / source	Low	Medium	High	XHigh	Max
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 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 2026-09-30.	Not reported	1,460.71 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	1,633.97 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	1,745.67 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	1,810.9 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	76% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	76.33% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	78% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	79.67% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	82.67% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	50.06% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	52.91% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	59.08% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	64.65% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	71.33% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-30.	11.43% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	16.86% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	24.57% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	31.14% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	31.43% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	16% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	20.2% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	25.2% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	24.6% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	25.8% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
GDPval-AA v2.1 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 DeepSeek V4.1 Flash (max) at 1,600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-09-30.	1,167.96 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	1,292.2 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	1,517.33 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	1,724.9 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	1,844.21 Elo Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	89.03% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	91.82% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	92.1% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	92.42% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	93.07% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	36.24% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	39.81% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	45.83% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	50% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	54.96% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	Not reported	75% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	19.37 Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	20.1 Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	20.95 Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	23.5 Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	32.3 Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	46.3% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	47.17% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	51.98% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	53.03% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	53.95% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-30.	49.07% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	52.89% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	53.7% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	57.29% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	61% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
Terminal-Bench-Science 0.1Artificial Analysis · mini-swe-agent; Terminal-Bench-Science 0.1.0; 70 tasks; pass@1 averaged over 3 repeats Benchmark details Share of tasks passed (pass@1), averaged over three repeats · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-09-30.	10.48% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	16.19% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	34.29% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	52.38% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	53.33% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	20.71% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-low	29.8% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-medium	43.94% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-high	57.07% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5-xhigh	63.64% Reported settings Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-sonnet-5-5
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 2026-09-30.	43.41% 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 0.004	50.46% 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 0.0053	61.46% 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 0.0067	64.43% 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	59.09% 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 0.0337
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 2026-09-30.	29.33% 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	36.48% 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	49.38% 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	52.09% 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	46.21% 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 0.0465
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 2026-09-30.	Not reported	Not reported	Not reported	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	84.78% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	86.96% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	92.96% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	95.78% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	98.5% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	99.33% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	90.94% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	40.62% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	100% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	97% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	36.36% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	77.27% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	80% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	82% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5
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 2026-09-30.	Not reported	Not reported	Not reported	97.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-sonnet-5-5-xhigh-effort; checkpoint=claude-sonnet-5-5	97.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; claude-sonnet-5-5-max-effort; checkpoint=claude-sonnet-5-5

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 · 8,147 results across 245 models · Collected 2026-09-30

Claude Sonnet 5.5

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results