RankingEffort benchmarks

Claude Opus 4.7

Compare models

91 measured results · 7 effort settings · 66 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 4.7 · XHigh3 of 7 capabilities supported

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

Agentic
A56.1Preliminary
Hard reasoning
A59.3Supported
Coding
A49.0Supported
Human pref
Unknown
Knowledge
A38.0Supported
Multimodal
Unknown
Long context
Unknown

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

Capability score evidence

Claude Opus 4.7 · XHigh: 38.7 overall comparison score. Meets the overall evidence requirements.

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

Which sources carry the weight?

Cognition · 46.4% direct comparison weight · independent of the model provider
LiveBench · 37.6% direct comparison weight · independent of the model provider
Epoch AI · 16.0% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

FrontierCode · 46.4% direct comparison weight
simpleqa · 16.0% direct comparison weight
livebench-coding · 5.4% direct comparison weight
livebench-data · 5.4% direct comparison weight
livebench-language · 5.4% direct comparison weight
Other families (4) · 21.5% 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 2026-10-23.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 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	81 → 83	Down 2	203 remaining / 241 lost	38.2 (-0.5 points)
ARC Prize	89 → 95	Down 6	444 remaining / 0 lost	40.9 (+2.2 points)
Datacurve	89 → 92	Down 3	444 remaining / 0 lost	34.9 (-3.8 points)
LiveCodeBench	89 → 89	No movement	444 remaining / 0 lost	38.7 (+0.0 points)
Scale	89 → 89	No movement	444 remaining / 0 lost	40.5 (+1.8 points)
Terminal-Bench	89 → 90	Down 1	444 remaining / 0 lost	38.3 (-0.4 points)
Cognition	89 → 65	Up 24	444 remaining / 0 lost	50.2 (+11.5 points)
LiveBench	89 → 103	Down 14	443 remaining / 1 lost	34.5 (-4.2 points)
SWE-rebench	89 → 89	No movement	444 remaining / 0 lost	38.1 (-0.6 points)
Epoch AI	88 → 91	Down 3	431 remaining / 13 lost	38.8 (+0.1 points)
Vals AI	89 → 89	No movement	443 remaining / 1 lost	37.4 (-1.3 points)
Provider reports · Anthropic	89 → 89	No movement	444 remaining / 0 lost	38.7 (-0.0 points)
Provider reports · Moonshot AI	89 → 90	Down 1	444 remaining / 0 lost	38.3 (-0.4 points)
Provider reports · Meta	89 → 89	No movement	444 remaining / 0 lost	38.7 (-0.0 points)
Provider reports · Mistral	89 → 89	No movement	444 remaining / 0 lost	38.7 (+0.0 points)
Provider reports · OpenAI	89 → 89	No movement	444 remaining / 0 lost	38.7 (+0.1 points)
All provider reports	89 → 90	Down 1	444 remaining / 0 lost	38.3 (-0.4 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	50.2	+11.5
deepswe	34.9	-3.8
livebench-language	40.3	+1.6
livebench-coding	37.1	-1.6
simpleqa	37.2	-1.5
mmmu-pro	39.9	+1.2
arc-agi	39.8	+1.1
hle	39.8	+1.1
gpqa	39.7	+1.0
livebench-instructions	39.7	+1.0
frontiermath	39.5	+0.8
livebench-math	37.9	-0.8
swe-rebench	38.1	-0.6
livebench-reasoning	38.1	-0.6
aime	39.2	+0.5
mmlu-pro	39.1	+0.4
multi-swe-bench	39.1	+0.4
swe-atlas-qna	38.4	-0.3
terminal-bench	38.5	-0.2
harvey	38.5	-0.2
briefcase	38.5	-0.2
arc-agi-3	38.5	-0.2
ifbench	38.5	-0.2
enigma-eval	38.5	-0.2
swe-atlas-test-writing	38.5	-0.2
vibe-code	38.5	-0.1
omniscience	38.8	+0.1
tau-bench	38.6	-0.1
gdp-pdf	38.8	+0.1
vals-finance-agent	38.6	-0.1
terminal-bench-science	38.6	-0.1
aa-lcr	38.8	+0.1
apex-agents	38.8	+0.1
vals-legal-research	38.6	-0.1
epoch-game-puzzles	38.6	-0.1
swe-atlas-refactoring	38.6	-0.1
critpt	38.7	+0.0
gdpval	38.7	-0.0
vals-excel-modeling	38.7	-0.0
vals-tax-agent	38.7	-0.0
itbench	38.7	-0.0
analyst-agent	38.7	-0.0
livebench-data	38.7	-0.0
swe-bench-pro	38.7	+0.0
automationbench	38.7	-0.0
vals-code-migration	38.7	+0.0
livecodebench	38.7	+0.0
gmmlu	38.7	+0.0
math500	38.7	-0.0
enterprise-ops	38.7	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 129 observations, 78 contributing, 0 matched without graph weight and 51 excluded. Counts do not establish rank eligibility.

5 · Benchmark family or source protocol has not been reviewed
1 · Run-specific qualification requires review: All incorrect answers were actually cases of the model failing to submit an answer. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign a score of 0. Then we average these scores across all samples. The resulting score is 44/45.
1 · Effort is not identified
1 · Fewer than two distinct model identities remain in this evaluation
5 · Evaluator has not been reviewed for independent admission
11 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
1 · MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology.
26 · 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	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	43.75% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	Not reported	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	1,254.06 Elo Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	1,067.85 Elo Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	78.67% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	75.67% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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. 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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	12% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	5.14% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	1,352.39 Elo Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	Not reported	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	91.41% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	88.48% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	42.31% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	33.32% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	58.64% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	43.61% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	46.66% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	Not reported	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	Not reported	28.89% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	78.84% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	76.36% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	27.27 Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	14.83 Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	48.88% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	44.73% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	88.6% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	73.98% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	34.64% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	Not reported	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	51.52% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	54.55% Reported settings Claude Opus 4.7 (Non-reasoning, High); Model source: https://artificialanalysis.ai/models/claude-opus-4-7-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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	83.15% Reported settings Claude Opus 4.7 (Max); Model source: https://artificialanalysis.ai/models/claude-opus-4-7	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 2026-10-18.	Not reported	Not reported	Not reported	Not reported	68.9% Reported settings Opus 4.7; Reported effort: max; 447 trials; recorded 2026-04-16	Not reported	Not reported
Terminal-Bench 2.1Terminal-Bench · Terminus 2 Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	Not reported	66.07% Reported settings Opus 4.7; Reported effort: max; 445 trials; recorded 2026-04-16	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 2026-10-18.	43.6% 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	44.75% 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	51.12% 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 0.0007	51.41% 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 0.0027	53.93% 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 0.0007	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 2026-10-18.	27.61% 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	28.91% Reported settings FrontierCode 1.1; main; 100 tasks; claude-code; source effort medium; weighted rubric score, not pass rate; unfair internet runs zeroed by evaluator; flag rate 0	35.17% 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 0.001	34.91% 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 0.004	38.54% 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 0.001	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 2026-10-18.	Not reported	Not reported	Not reported	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7	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 2026-10-18.	Not reported	Not reported	Not reported	78.26% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7	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 2026-10-18.	Not reported	Not reported	Not reported	85.92% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7	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 2026-10-18.	Not reported	Not reported	Not reported	92.33% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; claude-opus-4-7-xhigh-effort; checkpoint=claude-opus-4-7	Not reported	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 · 8,916 results across 259 models · Collected 2026-10-18

Claude Opus 4.7

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results