RankingEffort benchmarks

Claude Opus 5.5

Compare models

101 measured results · 6 effort settings · 33 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 Opus 5.5 · Max3 of 7 capabilities supported

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

Agentic
A73.8Supported
Hard reasoning
A78.6Supported
Coding
A92.9Supported
Human pref
Unknown
Knowledge
A90.4Preliminary
Multimodal
A75.6Preliminary
Long context
A77.1Preliminary

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 Opus 5.5 · Max: 92.1 overall comparison score. Meets the overall evidence requirements.

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

Which sources carry the weight?

Cognition · 28.0% direct comparison weight · independent of the model provider
ARC Prize · 24.2% direct comparison weight · independent of the model provider
Artificial Analysis · 24.1% direct comparison weight · independent of the model provider
Terminal-Bench · 23.7% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

FrontierCode · 28.0% direct comparison weight
Terminal-Bench · 24.5% direct comparison weight
ARC-AGI · 24.2% direct comparison weight
Humanity’s Last Exam · 2.0% direct comparison weight
Critpt · 2.0% direct comparison weight
Other families (11) · 19.2% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

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 2026-10-31.

Both ranks use the same surviving configurations for each removal. The cohort starts with 446 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	3 → 2	Up 1	203 remaining / 243 lost	94.3 (+2.2 points)
ARC Prize	3 → 6	Down 3	446 remaining / 0 lost	93.0 (+0.9 points)
Datacurve	3 → 4	Down 1	446 remaining / 0 lost	91.2 (-0.9 points)
LiveCodeBench	3 → 3	No movement	446 remaining / 0 lost	92.1 (-0.0 points)
Scale	3 → 4	Down 1	446 remaining / 0 lost	92.0 (-0.0 points)
Terminal-Bench	3 → 10	Down 7	446 remaining / 0 lost	87.0 (-5.1 points)
Cognition	3 → 2	Up 1	446 remaining / 0 lost	93.0 (+0.9 points)
LiveBench	3 → 3	No movement	445 remaining / 1 lost	93.1 (+1.0 points)
SWE-rebench	3 → 3	No movement	446 remaining / 0 lost	91.9 (-0.1 points)
Epoch AI	3 → 2	Up 1	433 remaining / 13 lost	92.6 (+0.5 points)
Vals AI	3 → 4	Down 1	445 remaining / 1 lost	91.7 (-0.4 points)
Provider reports · Anthropic	3 → 4	Down 1	446 remaining / 0 lost	91.8 (-0.3 points)
Provider reports · Moonshot AI	3 → 3	No movement	446 remaining / 0 lost	91.9 (-0.1 points)
Provider reports · Meta	3 → 3	No movement	446 remaining / 0 lost	92.0 (-0.0 points)
Provider reports · Mistral	3 → 3	No movement	446 remaining / 0 lost	92.1 (+0.0 points)
Provider reports · OpenAI	3 → 3	No movement	446 remaining / 0 lost	92.0 (-0.1 points)
All provider reports	3 → 4	Down 1	446 remaining / 0 lost	91.5 (-0.5 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
terminal-bench	87.0	-5.1
frontiercode	93.0	+0.9
itbench	93.0	+0.9
deepswe	91.2	-0.8
arc-agi	92.6	+0.6
harvey	92.5	+0.5
arc-agi-3	91.8	-0.3
briefcase	91.8	-0.2
swe-atlas-test-writing	91.9	-0.2
terminal-bench-science	91.9	-0.2
simpleqa	92.2	+0.2
livebench-instructions	92.2	+0.2
mmmu-pro	92.2	+0.2
ifbench	91.9	-0.2
livebench-coding	91.9	-0.2
livebench-data	92.2	+0.2
tau-bench	91.9	-0.2
swe-rebench	91.9	-0.1
gdpval	91.9	-0.1
epoch-game-puzzles	91.9	-0.1
aa-lcr	92.2	+0.1
automationbench	92.0	-0.1
swe-atlas-qna	92.0	-0.1
multi-swe-bench	92.0	-0.1
analyst-agent	92.0	-0.1
mmlu-pro	92.2	+0.1
gdp-pdf	92.2	+0.1
livebench-math	92.0	-0.1
omniscience	92.0	-0.1
gpqa	92.1	+0.1
vibe-code	92.0	-0.1
livebench-language	92.1	+0.1
frontiermath	92.0	-0.1
livebench-reasoning	92.0	-0.1
vals-finance-agent	92.1	+0.1
vals-tax-agent	92.0	-0.0
vals-excel-modeling	92.0	-0.0
vals-legal-research	92.0	-0.0
swe-atlas-refactoring	92.1	+0.0
aime	92.0	-0.0
critpt	92.1	+0.0
enigma-eval	92.1	+0.0
hle	92.0	-0.0
vals-code-migration	92.1	-0.0
livecodebench	92.1	-0.0
enterprise-ops	92.1	-0.0
gmmlu	92.1	-0.0
math500	92.1	-0.0
apex-agents	92.1	-0.0
swe-bench-pro	92.1	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 191 observations, 79 contributing, 0 matched without graph weight and 112 excluded. Counts do not establish rank eligibility.

7 · 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
7 · Evaluator has not been reviewed for independent admission
3 · Effort is not identified
43 · Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison.
1 · Provider-published lab self-report. Shown as a labeled claim and not admitted as a matched board comparison. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
17 · Provider-published claim. Independent source results are admitted separately with exact checkpoint, effort and compatible protocol; this grid does not establish a matched comparison.
1 · Provider-published claim. Independent source results are admitted separately with exact checkpoint, effort and compatible protocol; this grid does not establish a matched comparison. Historical provider claim; secondary and superseded for current FrontierSWE comparisons by the independent Proximal FrontierSWE v2 mean@5 board at https://www.frontierswe.com/. Version-unspecified claims are not v2 results. Excluded from weighted Overall.
11 · Combined fallback setup is not the named base model at one effort setting.
16 · Supporting evidence outside the reviewed capability core
1 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately

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.

Reviewed retained observations are in use. October 2026 Real-SWE board has no 95% confidence whisker, so these scores stay at the 2026-10-18 retrieval. Original source retrieval 2026-10-18; source updated 2026-10-18.

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 2026-10-31.	Not reported	Not reported	Not reported	Not reported	56.25% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
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 2026-10-31.	1,279.38 Elo Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	1,621.76 Elo Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	1,681.94 Elo Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	1,761.21 Elo Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	1,800.51 Elo Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	80.67% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	84.33% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	82.67% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	84.67% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	84.67% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	52.93% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	61.22% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	63.21% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	64.95% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	69.54% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	17.71% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	27.71% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	30.86% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	31.71% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	31.71% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
GDP.pdf: All-pass RateArtificial 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 2026-10-31.	25.6% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	25.6% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	28.8% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	26.6% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	26.2% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
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 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-31.	1,240.15 Elo Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	1,592.56 Elo Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	1,713.6 Elo Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	1,835.03 Elo Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	1,866.27 Elo Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
Harvey LAB-AA v1.1: Hallucination-Gated All-Pass RateArtificial Analysis · Stirrup; Harvey private dataset v1.1.0; 120 tasks across 24 practice areas; up to 200 turns; internet disabled; GPT-6 Sol, Grok 4.7 and Claude Opus 5.5 rubric judges; GPT-6 Sol High two-pass hallucination check; hallucination-gated all-pass averaged across judges Benchmark details Average over tasks of the share of the judge panel finding every rubric criterion passed, with a task zeroed on any material hallucination · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	4.17% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	48.33% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	54.73% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	55.56% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	57.51% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	61.35% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
ITBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	38.23% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of responses judged complete with no claim contradicting the record · Expert + compound (hard) sets · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-31.	19.44% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	22.22% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	15% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	25% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	27.78% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	84.68% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	85.72% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	85.84% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	86.59% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	87.69% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience v1.1 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 2026-10-31.	39.03 Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	39.77 Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	42.37 Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	43.13 Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	48.13 Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
AA-Omniscience AccuracyArtificial Analysis · 3000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience v1.1 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 2026-10-31.	63.33% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	63.9% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	64.83% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	65.53% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	65.5% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
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 2026-10-31.	58.56% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	59.26% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	60.42% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	65.05% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	66.9% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	Not reported
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 2026-10-31.	24.29% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	43.33% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	49.05% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	61.9% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	59.05% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	31.31% Reported settings Claude Opus 5.5 (Low, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-low	52.53% Reported settings Claude Opus 5.5 (Medium, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-medium	56.57% Reported settings Claude Opus 5.5 (High, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-high	59.6% Reported settings Claude Opus 5.5 (Xhigh, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5-xhigh	59.6% Reported settings Claude Opus 5.5 (Max, Default Fallback); Model source: https://artificialanalysis.ai/models/claude-opus-5-5	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 2026-10-31.	70.14% Reported settings Claude Opus 5.5 (Low); Source model ID: anthropic-claude-opus-5-5-low; 120 tasks	87.5% Reported settings Claude Opus 5.5 (Medium); Source model ID: anthropic-claude-opus-5-5-medium; 120 tasks	93.33% Reported settings Claude Opus 5.5 (High); Source model ID: anthropic-claude-opus-5-5-high; 120 tasks	92.5% Reported settings Claude Opus 5.5 (XHigh); Source model ID: anthropic-claude-opus-5-5-xhigh; 120 tasks	91.67% Reported settings Claude Opus 5.5 (Max); Source model ID: anthropic-claude-opus-5-5-max; 120 tasks	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 2026-10-31.	60.33% 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 0.0067	65.27% 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 0.004	65.2% 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	63.53% 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	63.58% 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
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 2026-10-31.	47.3% 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	54.64% 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	53.99% 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	51.42% 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	54.43% 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 0.008	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 2026-10-31.	Not reported	Not reported	Not reported	Not reported	64.8% Reported settings Terminal-Bench 4.0.0; 66 tasks; Claude Code; effort max; reported margin ±3.1 percentage points, confidence level unspecified; release date 2026-09-22; board checked 2026-10-23	Not reported
Artificial Analysis Cyber IndexArtificial Analysis · Artificial Analysis Stirrup; defensive code audit, patch and end-to-end vulnerability tasks Benchmark details v1.0. Equal mean of CWE-Bench-AA, DeepsecBench-AA and CyberGym-E2E-AA. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall. https://artificialanalysis.ai/methodology/cyber-index Unit: index. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	28.66 Reported settings Artificial Analysis Stirrup; v1.0; Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback); source label Claude Opus 5.5 (Max, Default Fallback); mitigation standard; public model; source field cyberIndex; index 0–100; CWE-Bench-AA pass@1 0.583333333333333; refusal 0.09166666666666666; DeepsecBench-AA median F2, 3 repeats, GPT-5.6 Sol High judge 0.26894153661864; refusal 0; CyberGym-E2E-AA pass@1 0.007633587786259542; refusal 0.9847328244274809; https://artificialanalysis.ai/models/claude-opus-5-5; page sha256 344ca66f5aa3f3abd1901b12bd29db73950d90e553fcb3ae900dcf590d7a6db2; encrypted payload sha256 b5e6ae259181eaed471e288c4bbdbd1088438e0a81caf19ec0fa60f7092d48f7; Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall.	Not reported
Bug Hunt BenchBug Hunt Bench · Native agentic CLI per row, blind judge against a withheld key. The CLI is named in each configuration. Benchmark details 105 planted bugs across two production repositories (45 and 60). Score is (fixed / 105) * 100, counting planted bugs fixed only. Primary rows are featured and not superseded. Display only pending comparability review. Many rows are single runs. Unit: percent. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	40.95% Reported settings Opus 5.5; Claude Code; effort max (first_party); source ceiling. Single run; fixed 43 of 105 planted bugs. partial 3; claimed_only 3; extras 9; evaluation 2026-09-22. Score is (fixed / 105) * 100. Extras, partials and claimed-only are not scored. Source caveat: ONE RUN, not a mean - and this board has already measured a 13-point spread between two runs of one identical max-effort configuration, so treat 43 as a single draw, not a settled level. Runs a 1M context window with zero compactions; [source caveat truncated].	Not reported
DAYJOB HealthcareSurge AI · OpenHands SDK 1.43.1 inside Harbor 0.22.0. Judge is Claude Opus 4.8. Score is the board's strict pass@1 percent. Benchmark details DAYJOB Healthcare strict pass@1 percent on the public Surge board. tau = 1, five attempts per task, 50 tasks in the paper and the Hugging Face dataset card. The page meta description says 65 assignments. That count is not on the scoreboard and is not used as n. An attempt passes only when every binary rubric criterion is met. Finance is a separate benchmark. Display only. Not an average and not GDPval-AA. Unit: percent. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	24.7% Reported settings Claude Opus 5.5; effort max. Strict pass@1 percent, tau = 1, five attempts, 50 DAYJOB: Healthcare tasks. An attempt passes only when every binary rubric criterion is met. OpenHands SDK 1.43.1 in Harbor 0.22.0. Judge: Claude Opus 4.8.	Not reported
DAYJOB FinanceSurge AI · OpenHands SDK 1.43.1 inside Harbor 0.22.0. Judge is Claude Opus 4.8. Score is the board's strict pass@1 percent. Benchmark details DAYJOB Finance strict pass@1 percent on the public Surge board. tau = 1, five attempts per task, 80 tasks in the paper and the Hugging Face dataset card. An attempt passes only when every binary rubric criterion is met. Healthcare is a separate benchmark. Display only. Not an average and not GDPval-AA. Unit: percent. Source collected 2026-10-31.	Not reported	Not reported	Not reported	Not reported	23.9% Reported settings Claude Opus 5.5; effort max. Strict pass@1 percent, tau = 1, five attempts, 80 DAYJOB: Finance tasks. An attempt passes only when every binary rubric criterion is met. OpenHands SDK 1.43.1 in Harbor 0.22.0. Judge: Claude Opus 4.8.	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 · 8,399 results across 259 models · Collected 2026-10-31

Claude Opus 5.5

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results