competition · audited-with-caveats · verified 2026-07-21

CASP

Biennial blind community experiments that assess macromolecular structure, complex, ligand, and model-accuracy prediction against experimental structures withheld during prediction.

+3 more

Nucleic-acid result atlas: B14 results (family_member) · B15 results (family_member)

Audited with caveats: 1 field(s) are marked provisional or conflicted. Warnings are shown next to affected values and these claims are excluded from unqualified comparisons.

Round and count audit: CASP17 is an active, rolling 2026 round; all displayed CASP17 counts are dated to 2026-07-21. CASP16 is the latest completed round. Phase releases, unique targets, assessment units, and ligand cases use different bases and are never summed into a synthetic total.

Benchmark definition

What is counted

Version: CASP17
Total: Not reported (round-specific target releases; categories and repeated phases overlap)
Task formats: blind structure prediction; blind complex prediction; blind ligand pose and affinity prediction; model accuracy estimation
Capabilities: Prediction
Modalities: Protein sequenceDNA or RNA sequence3D structure

Version history

Version	Status	Release / as-of	Total	Formal tracks
CASP16 `casp-suite-casp16`	superseded	2024-05-01	Not reported (target releases across overlapping categories and phases)	casp-protein-monomers, casp-protein-multimers, casp-protein-ligands
CASP17 `casp-suite-casp17`	rolling	2026-04-27	Not reported (round-specific target releases; categories and repeated phases overlap)	casp-protein-monomers, casp-protein-multimers, casp-protein-ligands

Tracks and subsets

ID	Count	Basis	Partition?	Notes
CASP17 protein targets released without stoichiometry `casp17-protein-no-stoichiometry`	75	target releases	No	Includes monomers and multimers; it must not be added to the with-stoichiometry count.
CASP17 protein targets released with stoichiometry `casp17-protein-with-stoichiometry`	61	multimer target re-releases	No	Multimer targets only; these overlap with targets released earlier without stoichiometry.
CASP17 RNA targets `casp17-rna-targets`	45	target releases	No	Includes RNA monomers and multimers.
CASP17 protein-RNA-DNA hybrid targets `casp17-hybrid-targets`	8	target releases	No	—

Registered child tracks

CASP Protein-Ligand Prediction

Formal CASP track for blind prediction of protein-ligand binding poses, binding affinity or rank, binding pockets, and pose confidence.

3 evaluation run(s)

CASP Protein Monomers

Formal CASP track assessing blind predictions of single-protein structures and post hoc protein evaluation units against withheld experimental coordinates.

1 evaluation run(s)

CASP Protein Multimers

Formal CASP track assessing blind protein-complex predictions, including overall folds, interfaces, stoichiometry-free phases, and model-selection phases.

1 evaluation run(s)

Scientific Task Atlas

Scientific task classification

partial for CASP17 · as of 2026-07-21. CASP17 is active; mappings follow formal categories while final assessed target counts remain unavailable.

Scientific task	Coverage	Count	Mapping	Evidence
Protein monomer structure prediction	explicitly-in-scope	Not reported CASP17 assessed monomer evaluation units.	official-track high confidence	`casp-evidence-casp17-protocol` The final assessed monomer count is not yet reported.
Protein complex structure prediction	explicitly-in-scope	61 targets CASP17 multimer target re-releases with stoichiometry as of 2026-07-21.	official-track high confidence	`casp-evidence-casp17-counts` Rolling release count; not a final assessed-set total.
Protein model quality assessment	explicitly-in-scope	Not reported CASP17 model-selection and accuracy-estimation targets.	official-track high confidence	`casp-evidence-casp17-protocol` No final current-round count is asserted.
Protein-ligand pose prediction	explicitly-in-scope	Not reported CASP17 protein-ligand targets.	official-track high confidence	`casp-evidence-casp17-protocol` Pose prediction is a formal ligand-category objective.
Protein-ligand binding affinity	explicitly-in-scope	Not reported CASP17 protein-ligand targets.	official-track high confidence	`casp-evidence-casp17-protocol` Affinity or rank prediction is a formal ligand-category objective.

Scientific coverage notes

Domain	Coverage	Count	Interpretation
Protein-protein binding	explicitly-in-scope	61	CASP17 reports 61 multimer targets re-released with stoichiometry as of 2026-07-21; this is a rolling target-release count, not an evaluated final set.
Antibody-antigen	explicitly-in-scope	Not reported	Immune complexes are a dedicated CASP17 category, but the official in-numbers page does not publish a separate immune-complex count.
Protein-ligand binding	explicitly-in-scope	Not reported	Organic ligand-protein complexes are a dedicated CASP17 category, but no current ligand-only target count is published on the CASP17 in-numbers page.

Evaluation registry

Works and run settings

A setting change—scope, prompt, tools, budget, grader, or repeats—creates a separate run. Charts never cross a comparability group.

Evaluation run

casp16-ligand-affinity-stage1

From Assessment of Pharmaceutical Protein-Ligand Pose and Affinity Predictions in CASP16

Scopesubset · n=122

ShotsNot applicable

TurnsNot applicable

System prompt publicNot applicable

Reasoning / effortNot applicable

Browsermethod-specific

Internetmethod-specific

Databasesmethod-specific

Code executionallowed

ContainerNot reported

External toolsmethod-specific

Token budgetNot applicable

Time / cost budgettarget-specific CASP submission windows before experimental poses were released

TemperatureNot applicable

SeedNot reported

RepeatsModel 1 affinity submission per group and case

Graderofficial affinity ranking analysis plus independent ligand assessor team · human review: yes

StatisticsN-weighted Kendall tau across the two protein systems after disclosure filtering

Contaminationexperimental poses and affinities withheld, with 18 previously disclosed affinities removed from analysis

Metrics, results, and full protocol

Metrics

Metric	Kind / baseline	Unit	Aggregation	Threshold / tolerance
N-weighted Kendall's tau	absolute	rank correlation	case-count-weighted mean of per-protein-system Kendall tau after disclosure filtering	Not reported

No numeric result rows are published yet; the verified protocol remains useful.

Evidence

section: Sections 2.2–2.5 and 3.3; Figure 8A (Original 140 cases, 18 disclosure exclusions, Stage-1 setting, Model 1, and N-weighted Kendall tau.) — supports /benchmark_version, /scope, /protocol, /metrics

Evaluation run

casp16-ligand-affinity-stage2

From Assessment of Pharmaceutical Protein-Ligand Pose and Affinity Predictions in CASP16

Scopesubset · n=103

ShotsNot applicable

TurnsNot applicable

System prompt publicNot applicable

Reasoning / effortNot applicable

Browsermethod-specific

Internetmethod-specific

Databasesmethod-specific

Code executionallowed

ContainerNot reported

External toolsmethod-specific

Token budgetNot applicable

Time / cost budget2024-08-07 through 2024-08-21 for the main Stage-2 challenge

TemperatureNot applicable

SeedNot reported

RepeatsModel 1 affinity submission per group and case

Graderofficial affinity ranking analysis plus independent ligand assessor team · human review: yes

Statisticsper-system Kendall tau and N-weighted cross-system summary after disclosure filtering

Contaminationexperimental co-crystal structures provided while experimental affinities remained withheld; disclosed affinities removed

Metrics, results, and full protocol

Metrics

Metric	Kind / baseline	Unit	Aggregation	Threshold / tolerance
N-weighted Kendall's tau	absolute	rank correlation	case-count-weighted mean of per-protein-system Kendall tau after disclosure filtering	Not reported

No numeric result rows are published yet; the verified protocol remains useful.

Evidence

section: Sections 2.2–2.5 and 3.3; Figures 8B-C and 9 (110 releases, 103 retained cases, co-crystal structure access, Stage-2 dates, and Kendall tau analysis.) — supports /benchmark_version, /scope, /protocol, /metrics

Evaluation run

casp16-ligand-pose-regular

From Assessment of Pharmaceutical Protein-Ligand Pose and Affinity Predictions in CASP16

Scopesubset · n=229

ShotsNot applicable

TurnsNot applicable

System prompt publicNot applicable

Reasoning / effortNot applicable

Browsermethod-specific

Internetmethod-specific

Databasesmethod-specific

Code executionallowed

ContainerNot reported

External toolsmethod-specific

Token budgetNot applicable

Time / cost budgettarget-specific CASP submission windows

TemperatureNot applicable

SeedNot reported

Repeatsup to five pose models per target

Graderofficial OpenStructure ligand and binding-pocket scoring plus independent ligand assessor team · human review: yes

Statisticsmean per-group pose accuracy with explicit handling of skipped targets; Model 1 is the primary ranking view

Contaminationexperimental complex poses withheld during Stage 1 prediction; structural template similarity analyzed post hoc

Metrics, results, and full protocol

Metrics

Metric	Kind / baseline	Unit	Aggregation	Threshold / tolerance
LDDT-PLI	absolute	proportion	mean across eligible pose targets with missing-prediction handling	CASP16 modified the CASP15 definition to penalize erroneous non-native contacts.
BiSyRMSD	absolute	angstrom	per pose then group summary	symmetry-corrected after binding-site superposition
LDDT-lp	absolute	proportion	per binding pocket then group summary	Not reported
BB-RMSD	absolute	angstrom	binding-site C-alpha RMSD then group summary	Not reported

No numeric result rows are published yet; the verified protocol remains useful.

Evidence

section: Abstract; Sections 2.1–2.5 and 3.1–3.2 (229 assessed pose cases, participant protocol, Model 1 handling, pose metrics, missing submissions, and separate baselines.) — supports /benchmark_version, /scope, /protocol, /metrics

Evaluation run

casp16-monomer-regular-official

From CASP16 Protein Monomer Structure Prediction Assessment

Scopefull · n=54

ShotsNot applicable

TurnsNot applicable

System prompt publicNot applicable

Reasoning / effortNot applicable

Browsermethod-specific

Internetmethod-specific

Databasesmethod-specific

Code executionallowed

ContainerNot reported

External toolsmethod-specific

Token budgetNot applicable

Time / cost budgetapproximately three weeks per target for regular groups

TemperatureNot applicable

SeedNot reported

Repeatsup to five submitted models per target

Graderofficial CASP structure-comparison pipeline plus independent monomer assessor team · human review: yes

Statisticsper-evaluation-unit scores converted to group ranking summaries including cumulative clipped z-scores

Contaminationexperimental structures withheld until prediction closes

Metrics, results, and full protocol

Metrics

Metric	Kind / baseline	Unit	Aggregation	Threshold / tolerance
GDT_TS	absolute	score	computed per evaluation unit; official group rankings use first/best model views and z-score summaries	Not reported
GDT_HA	absolute	score	per evaluation unit	Not reported
lDDT	absolute	proportion	per evaluation unit	Not reported
TM-score	absolute	proportion	per evaluation unit	Not reported
SUM Z-score (> -2.0)	absolute	z-score sum	sum across eligible evaluation units after clipping values below -2.0	Not reported

No numeric result rows are published yet; the verified protocol remains useful.

Evidence

section: Results and Discussion; performance evaluation and ranking (54 evaluation units, model-1/best-model analyses, metrics, and assessor interpretation.) — supports /benchmark_version, /scope, /protocol/grader, /protocol/statistical, /metrics
section: Registration; Targets; Model submission/format; Assessment (Blind targets, regular versus server settings, deadlines, and independent assessment.) — supports /protocol/shots, /protocol/turns, /protocol/system_prompt_public, /protocol/reasoning, /protocol/tools, /protocol/token_budget, /protocol/time_budget, /protocol/temperature, /protocol/seed, /protocol/repeats, /protocol/contamination

Evaluation run

casp16-multimer-phase1-regular

From Assessment of Protein Complex Predictions in CASP16: Are We Making Progress?

Scopefull · n=40

ShotsNot applicable

TurnsNot applicable

System prompt publicNot applicable

Reasoning / effortNot applicable

Browsermethod-specific

Internetmethod-specific

Databasesmethod-specific

Code executionallowed

ContainerNot reported

External toolsmethod-specific

Token budgetNot applicable

Time / cost budgetapproximately three weeks per target for regular groups

TemperatureNot applicable

SeedNot reported

Repeatsup to five standard models per target

Graderofficial CASP/OpenStructure and CAPRI-compatible scoring plus independent complex assessor team · human review: yes

Statisticscumulative per-target z-scores and head-to-head comparisons; rankings reported for first and best models

Contaminationexperimental complex structures withheld until prediction closes

Metrics, results, and full protocol

Metrics

Metric	Kind / baseline	Unit	Aggregation	Threshold / tolerance
DockQ	absolute	proportion	per target followed by cumulative z-score ranking	0.5
TM-score	absolute	proportion	per target followed by cumulative z-score ranking	Not reported
lDDT	absolute	proportion	per target followed by cumulative z-score ranking	Not reported
ICS	absolute	F1 score	per target followed by cumulative z-score ranking	Not reported
IPS	absolute	Jaccard score	per target followed by cumulative z-score ranking	Not reported
QSbest	absolute	Jaccard score	per target followed by cumulative z-score ranking	Not reported

No numeric result rows are published yet; the verified protocol remains useful.

Evidence

section: Overview of targets; Phase 1 Ranking; Performance Evaluation and Ranking (40 Phase-1 targets, supplied stoichiometry, overall/interface metrics, first/best model analyses, and group ranking aggregation.) — supports /benchmark_version, /scope, /protocol/grader, /protocol/statistical, /metrics
section: Protein Complexes; Registration; Model submission/format; Assessment (Blind regular-group protocol, participant method freedom, deadlines, and assessors.) — supports /protocol/shots, /protocol/turns, /protocol/system_prompt_public, /protocol/reasoning, /protocol/tools, /protocol/token_budget, /protocol/time_budget, /protocol/temperature, /protocol/seed, /protocol/repeats, /protocol/contamination

Evidence and change history

Source locators remain visible; expand an item to inspect the exact Registry fields it supports.

casp1-history-resource · section: CASP1 description (Reports the first large-scale experiment in 1994, 33 targets, 35 groups, and independent assessment teams; no exact start day is given.) · Supports 6 fields

Open source →

/name
/aliases
/organizations
/release_date
/kind
/summary

CASP16 official competition and results archive · section: Description; Modeling categories; Timetable; Targets; Assessment; Results (Completed-round scope, blind protocol, categories, independent assessors, access, and first-target date.) · Supports 11 fields

Open source →

/domains
/capabilities
/modalities
/task_formats
/access
/access/level
/access/license
/resources
/implementations
/versions/0/release_date
/versions/0/formal_tracks

casp16-numbers-resource · table: CASP16 in numbers (Reports 156 tertiary, 108 multimer, 8 incidental ligand, 233 pharma pose, 140 pharma affinity, and 110 stage-2 affinity target releases, plus submission counts.) · Supports 3 fields

Open source →

/versions/0/task_counts/total
/versions/0/task_counts/basis
/versions/0/task_counts/subsets

CASP17 official competition · section: Description; Modeling categories; Timetable; Targets; Assessment; Results (Defines the active CASP17 round, dedicated immune and ligand categories, difficult structures/complexes, release schedule, and independent assessors.) · Supports 10 fields

Open source →

/latest_version
/domains
/coverage_notes
/versions/1/release_date
/versions/1/as_of
/versions/1/formal_tracks
/scientific_task_classification/entries/0
/scientific_task_classification/entries/2
/scientific_task_classification/entries/3
/scientific_task_classification/entries/4

casp17-numbers-resource · table: CASP17 in numbers, accessed 2026-07-21 (Rolling counts: 75 protein targets without stoichiometry, 61 multimer re-releases with stoichiometry, 45 RNA targets, and 8 hybrids.) · Supports 8 fields

Open source →

/task_counts/total
/task_counts/basis
/task_counts/subsets
/coverage_notes/0
/versions/1/task_counts/total
/versions/1/task_counts/basis
/versions/1/task_counts/subsets
/scientific_task_classification/entries/1

Unresolved field claims

/release_dateProvisional · medium — The official CASP1 history reports only the year 1994; 1994-01-01 is a machine-readable year-normalized date and not an asserted day of first target release.
Evidence: casp-evidence-origin

View source-level modification history on GitHub →

Access & reproducibility

Access: Partially open
License: CC BY 4.0 for Prediction Center website content; linked target and prediction artifacts may have separate terms
Grader: Category-specific numerical pipelines and independent assessor teams; no single round-indepen…
Implementations: 1 recorded · official

Access details

Tasks: Target sequences and submission metadata are public during a round; experimental structures are intentionally withheld until prediction closes.
Artifacts: Completed-round targets, submitted predictions, numerical score tables, rankings, presentations, and round archives are publicly linked; some source structures or pharmaceutical data may retain provider-specific terms.
Grader: Category-specific numerical pipelines and independent assessor teams; no single round-independent grader or metric exists.
Biosafety: The registry mirrors no target sequences, structures, ligand sets, or submitted models; active targets can include viral, immune, or drug-design systems.

Resources & implementations

Primary resources

casp-series-resource · CC BY 4.0 (website)
website · checked 2026-07-21
casp1-history-resource · CC BY 4.0 (website)
documentation · snapshot CASP1-1994 · checked 2026-07-21
casp16-home-resource · CC BY 4.0 (website)
website · snapshot CASP16 · checked 2026-07-21
casp16-numbers-resource · CC BY 4.0 (website)
documentation · snapshot CASP16-final · checked 2026-07-21
casp16-results-resource · CC BY 4.0 (website)
leaderboard · snapshot CASP16-results · checked 2026-07-21
casp16-download-resource
dataset · snapshot CASP16-download-archive · checked 2026-07-21
casp17-home-resource · CC BY 4.0 (website)
website · checked 2026-07-21
casp17-numbers-resource · CC BY 4.0 (website)
documentation · snapshot 2026-07-21 · checked 2026-07-21
casp17-target-list-resource · CC BY 4.0 (website metadata)
dataset · snapshot 2026-07-21 · checked 2026-07-21

Implementations

Prediction Center result and assessment system
official