RankingClaude Opus 5

Claude Opus 5

Data updated 22 Oct 2026

78 published benchmark measures · 22 benchmark families contribute across 6 task areas. 4 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Current configurationSources

Compare with

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

Compare withModel and configuration

Choose a configuration to compare. The overview below combines evidence across settings and has no model-wide rank.

Model evidence summary

This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →

Performance profile

Capabilities

Adjusted comparison score · 0–100

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic8 families · 2 with independent evidence · Supported82.9

8 core families; 54 direct opponents across 17 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 79.3–88.3; 0/13 scenarios unsupported. Without one publisher: 77.4–87.3; 0/15 unsupported. Smoothing check: 74.4–87.3; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

OSWorld: 63.7 observed win share
Anthropic, Meta, OpenAI, os-world.github.io · Source 1 Source 2 Source 3 Source 4 Source 5 Source 6
GDPval: 91.7 observed win share
Anthropic, Google, Meta, artificialanalysis.ai · Source 1 Source 2 Source 3 Source 4
AutomationBench: 72.2 observed win share
Anthropic, Meta, OpenAI · Source 1 Source 2 Source 3
OfficeQA: 0.0 observed win share
Anthropic · Source 1 Source 2
GDP.pdf: 80.0 observed win share
Google · Source 1
DeepSearchQA: 50.0 observed win share
Meta · Source 1
Browsecomp: 66.7 observed win share
OpenAI · Source 1
Terminal-Bench Science: 50.0 observed win share
OpenAI · Source 1

Hard reasoning4 families · 1 with independent evidence · Supported75.3

4 core families; 60 direct opponents across 10 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 60.8–80.1; 0/6 scenarios unsupported. Without one publisher: 67.6–77.8; 0/16 unsupported. Smoothing check: 68.5–78.6; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

GPQA: 65.0 observed win share
OpenAI, artificialanalysis.ai · Source 1 Source 2
ARC-AGI: 69.4 observed win share
Anthropic, OpenAI, arcprize.org · Source 1 Source 2 Source 3 Source 4 Source 5 Source 6
Humanity’s Last Exam: 31.1 observed win share
Anthropic, Google, OpenAI · Source 1 Source 2 Source 3 Source 4
FrontierMath: 0.0 observed win share
OpenAI · Source 1

Coding4 families · 2 with independent evidence · Supported92.7

4 core families; 35 direct opponents across 9 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 88.2–94.6; 0/6 scenarios unsupported. Without one publisher: 87.5–93.9; 0/19 unsupported. Smoothing check: 84.3–96.3; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Terminal-Bench: 72.7 observed win share
Anthropic, Google, OpenAI, tbench.ai · Source 1 Source 2 Source 3 Source 4
DeepSWE: 76.3 observed win share
OpenAI, deepswe.datacurve.ai · Source 1 Source 2
SWE-bench Multilingual: 100.0 observed win share
Anthropic · Source 1
SWE-bench Pro: 33.3 observed win share
Anthropic · Source 1

Human pref1 families · 1 with independent evidence · PreliminaryUnknown

1 core families; 76 direct opponents across 17 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Human preference (Arena): 97.4 observed win share
lmarena.ai · Source 1

Knowledge2 families · 0 with independent evidence · PreliminaryUnknown

2 core families; 2 direct opponents across 1 labs. No connected comparison to the complete reference panel

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Gmmlu: 0.0 observed win share
Anthropic · Source 1
Milu: 0.0 observed win share
Anthropic · Source 1

Multimodal3 families · 0 with independent evidence · Preliminary49.4

3 core families; 7 direct opponents across 3 labs. Needs broader benchmark and opponent support

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Chartography: 0.0 observed win share
Anthropic · Source 1 Source 2
CharXiv: 20.0 observed win share
Google · Source 1
Lvbench: 100.0 observed win share
Google · Source 1

Long contextNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

Reported effort · Mixed settings

Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

Auto thinking: 2 observations
Max: 19 observations
Not specified: 100 observations

Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

Inspect each result and its source ↓ · Download effort evidence

Score contributions and missing evidence

22 contributing families across 6 capabilities. Fixed reference panels do not change when the catalog expands.

Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

Model information & shareable badge

Lab: Anthropic
Catalog status: active
Availability: Public provider catalog; account and region restrictions may apply
Family: Claude Opus
Released: —
Context: 1,000,000 tokens
License: proprietary
Model card: https://platform.claude.com/docs/en/about-claude/model-deprecations
Default Capability family coverage: /badge/claude-opus-5.svg

Benchmark scores & sources

Original results, evaluation harnesses, and evidence behind this model.

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
AA-Briefcase	Supporting evidence	1685 Reported settings & source Artificial Analysis long-horizon knowledge projects; rubric and panel pairwise judging; Claude max effort. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.15.4 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
AA-Briefcase	Supporting evidence	57.2% Reported settings & source Artificial Analysis; max effort; component rubric pass. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.15.4 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
AA-Briefcase	Supporting evidence	1980 rating Reported settings & source Artificial Analysis; max effort; component analytical quality. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.15.4 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
AA-Briefcase	Supporting evidence	1572 rating Reported settings & source Artificial Analysis; max effort; component presentation. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.15.4 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
Agentic IF Index · internal	Supporting evidence	59.1 index Reported settings & source Internal composite instruction-following evaluations; no fixed task count; reasoning max Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.	Reviewed 2026-09-06
Agents' Last Exam	Supporting evidence	32.2%	Agents' Last Exam · Claude Code Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-20
Agents' Last Exam · not specified	Supporting evidence	55.5% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Computer Use table / Agents' Last Exam / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
ARC-AGI · 1	Hard reasoning	97.5% Reported settings & source ARC Prize semi-private validation; verified Fable5.1 max effort; comparator figures as reported in summary. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.16 · reviewed 2026-10-18	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-10-18
ARC-AGI · 2	Hard reasoning	90.42% Reported settings & source ARC Prize semi-private validation; verified Fable5.1 max effort; comparator figures as reported in summary. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.16 · reviewed 2026-10-18	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-10-18
ARC-AGI-1 · 1	Hard reasoning	97.5% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-1 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
ARC-AGI-2	Hard reasoning	90.4%	ARC Prize verified Effort: Not specified contributes to capability	official board	2026-07-24
ARC-AGI-2 · 2	Hard reasoning	90.4% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-2 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
ARC-AGI-3 · 3	Hard reasoning	30.2% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Abstract Reasoning table / ARC-AGI-3 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Artificial Analysis Coding Agent Index v1.4 · v1.4	Supporting evidence	68.1 index score Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Coding table / Artificial Analysis Coding Agent Index v1.4 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.	Reviewed 2026-09-06
Artificial Analysis Intelligence Index	Supporting evidence	63	AA Intelligence Index Effort: Not specified	official board Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit. Composite index excluded to avoid double counting its ingredients.	2026-08-12
Artificial Analysis Intelligence Index v4.1.1 · v4.1.1	Supporting evidence	63.1 index score Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Professional table / Artificial Analysis Intelligence Index v4.1.1 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Composite index or publisher-specific internal evaluation lacks a stable general-capability comparison unit.	Reviewed 2026-09-06
AutomationBench	Agentic	26.9% Reported settings & source Private held-out board; simulated business-workflow app APIs; all assertions must pass; max effort stated for Fable5.1/Opus5. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.1.A;8.15.6 · reviewed 2026-10-18	Published configuration Effort: Max contributes to capability	lab self-report	Reviewed 2026-10-18
AutomationBench · not specified	Agentic	26.9% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API Provider-published result; comparator measurements are not automatically independently reproduced. GPT-6 Astra: A new generation of intelligence · Professional table / AutomationBench / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
AutomationBench · public v3	Agentic	50.3% Reported settings & source 600public workflow tasks; deterministic end-state assertions;pass@1; reasoning max Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
AutomationBench-AA	Supporting evidence	56.57355576493251%	Artificial Analysis AutomationBench-AA Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-20
AutoResearchExam	Supporting evidence	0.579	AutoResearchExam Terminus 2 Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-09
BenchCAD · not specified	Supporting evidence	82.1% Reported settings & source Maximum reported across reasoning efforts; OpenAI research environment or API; tools enabled; three Anthropic evaluation modifications Provider-published result; comparator measurements are not automatically independently reproduced. Astra launch footnote5: Claude scores use three modifications described in the Fable5.1 system card; not same controlled setting. GPT-6 Astra: A new generation of intelligence · Professional table / BenchCAD / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
BenchCAD · Vision2Code 1000-file subset	Supporting evidence	0.366 voxel IoU Reported settings & source Random1000 of17900files; five runs; adaptive thinking max; no tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
BenchCAD · Vision2Code 1000-file subset	Supporting evidence	0.821 voxel IoU Reported settings & source Random1000 of17900files; five runs; adaptive thinking max; with tools; corrected camera prompt, raw shapes accepted, last code fence parsed. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.2 · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
BioMysteryBench · Human Difficult	Supporting evidence	51.8% Reported settings & source Anthropic life-sciences evaluation; bash/editor/packages except protein design no tools; protocols use bash/editor/search; Understanding revised network restriction. Internal evaluation; not necessarily publicly released; compare only same task/grader revision. Percent rank correlation is not accuracy. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.19 · reviewed 2026-10-18	Published configuration Effort: Not specified	lab self-report Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.	Reviewed 2026-10-18