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 →

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
SWE-bench Multimodal	Supporting evidence	59.4% Reported settings & source Anthropic reported configuration; adaptive thinking at max effort, default sampling, five-trial mean unless section specifies otherwise; context at most 1M. Comparator configuration follows cited prior card or board. Agent identity is not established as mini-swe-agent. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table 8.1.A; section 8.2 · reviewed 2026-10-18	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-10-18
SWE-bench Pro	Coding	79.2%	SWE-bench Pro reported Effort: Not specified	lab self-report Legacy self-report lacks a reviewed comparison configuration	2026-07-24
SWE-bench Pro	Coding	79.2% Reported settings & source Anthropic reported configuration; adaptive thinking at max effort, default sampling, five-trial mean unless section specifies otherwise; context at most 1M. Comparator configuration follows cited prior card or board. Agent identity is not established as mini-swe-agent. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table 8.1.A; section 8.2 · reviewed 2026-10-18	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-10-18
SWE-bench Verified	Coding	96%	SWE-bench Verified official Effort: Not specified	lab self-report Legacy self-report lacks a reviewed comparison configuration	2026-07-24
SWE-sweep	Supporting evidence	1.28%	SWE-sweep · xhigh Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-09-24
Terminal-Bench · 2.1	Coding	89.1% Reported settings & source Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Terminal-Bench coding slot admits version 4.0 only. Earlier versions remain stored and are not mixed into that slot.	Reviewed 2026-09-06
Terminal-Bench · 2.1	Coding	86.7% Reported settings & source 89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning max; native harness family: Anthropic (exact harness revision not specified) Native harnesses differ; not a Terminus2-only comparison. Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Different native coding harnesses are mixed; exact shared agent configuration is not established.	Reviewed 2026-09-06
Terminal-Bench · 4.0	Coding	52.3% Reported settings & source Claude Code --bare max effort, 15 trials/task over 66 tasks; Anthropic internal reruns. Uses more precise section values rather than rounded headline table. Distinct from2.1; timeouts/resources changed. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.6 · reviewed 2026-10-18	Published configuration Effort: Max contributes to capability	lab self-report	Reviewed 2026-10-18
Terminal-Bench · 4.0	Coding	51.8% Reported settings & source Officialpublicboard highest scoring thinking level; nativeagents may differ Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench 4.0	Coding	53.94%	Terminal-Bench 4.0 reported Effort: Not specified contributes to capability	official board	2026-07-24
Terminal-Bench 4.0 · 4.0	Coding	52.6% 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 / Terminal-Bench 4.0 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench Science 0.1 · not specified	Agentic	30% 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 · Academic table / Terminal-Bench Science 0.1 / Claude Opus 5 · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Terminal-Bench-Science · 0.1	Coding	29% Reported settings & source 70tasks; Claude Code --bare max; Fable10trials/task, Opus12; GPT Codex CLI max from public board. Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.7 · reviewed 2026-10-18	Published configuration Effort: Not specified	lab self-report Terminal-Bench coding slot admits version 4.0 only. Earlier versions remain stored and are not mixed into that slot.	Reviewed 2026-10-18
ThinkingBox-Bench	Supporting evidence	66.5%	ThinkingBox-Bench pass@1 Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-10-03
Toolathlon · Verified June2026	Agentic	80.6% Reported settings & source Pass@1;108tasks/three trials; internal harness; max effort; Fable safeguards+Opus4.8fallback; Opus safeguards/fallback disabled; pinned containers/data. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.15.5.A · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report No matched opponent in this evaluation unit	Reviewed 2026-10-18
Toolathlon · Verified June2026	Agentic	87% Reported settings & source Pass@3;108tasks/three trials; internal harness; max effort; Fable safeguards+Opus4.8fallback; Opus safeguards/fallback disabled; pinned containers/data. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.15.5.A · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report No matched opponent in this evaluation unit	Reviewed 2026-10-18
Toolathlon · Verified June2026	Agentic	73.1% Reported settings & source Pass³;108tasks/three trials; internal harness; max effort; Fable safeguards+Opus4.8fallback; Opus safeguards/fallback disabled; pinned containers/data. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.15.5.A · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report No matched opponent in this evaluation unit	Reviewed 2026-10-18
Toolathlon · Verified June2026	Agentic	23.5 turns Reported settings & source average turns;108tasks/three trials; internal harness; max effort; Fable safeguards+Opus4.8fallback; Opus safeguards/fallback disabled; pinned containers/data. Claude Fable 5.1 and Claude Mythos 5.1 System Card · Table8.15.5.A · reviewed 2026-10-18	Published configuration Effort: Max	lab self-report Metric turns is outside the task-success core	Reviewed 2026-10-18
VulcanBench v3	Supporting evidence	78.3%	VulcanBench v3 bare-bones API · Report 10 · high Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-26
VulcanBench v3	Supporting evidence	87%	VulcanBench v3 bare-bones API · Report 10 · low Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-26
VulcanBench v3	Supporting evidence	82.6%	VulcanBench v3 bare-bones API · Report 10 · medium Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-26
LiveCodeBench	Coding	—	—	—	—
MMLU-Pro	Knowledge	—	—	—	—
Terminal-Bench 2.1	Agentic	—	—	—	—