ctxdexSynthetic model data for learning

Benchmark definition

GPQA

ActiveEstablishedCommon useGPQA

A graduate-level, four-option science Q&A benchmark designed to resist simple web lookup.

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.

Compare with others

About

Description
GPQA contains expert-written graduate-level questions in biology, physics, and chemistry. Its construction was designed to require domain expertise rather than straightforward retrieval.
What it measures
Graduate-level scientific knowledge and reasoning in biology, physics, and chemistry.
What it does not measure
It does not cover broad non-science domains or interactive/agentic behavior.
Comparison guidance
Not published
Intended difficulty
Not published

Not recorded for this benchmark: why it matters, motivation, gap addressed.

Classification

Categories
KnowledgeScience reasoningGeneral reasoning
Domains
BiologyPhysicsChemistry
Evaluation style
Automatic reference matchStatic Q&A

Structure

3 components. Applicability can differ between them.

Components

  • MainSubset448-question main set.
  • ExtendedSubset546-question extended set.
  • DiamondSubset198-question high-quality/hard subset represented separately as an exact CTXDEX BenchmarkDefinition.

Tasks

Graduate-level science multiple-choice Q&A

Metrics

What a result on this benchmark would be reported as. ctxdex does not carry results.

MetricRoleDirectionUnit
Accuracy
PrimaryHigher is betterPercent

Methodology

GPQA reference evaluationThis definition

The official repository supports zero-shot, few-shot, chain-of-thought, and retrieval-based baselines; these are methodology variants, not separate benchmark identities.

Evaluation environment

What the benchmark's harness provides and allows. These are properties of the environment, not model requirements, and applicability does not test for them.

Interaction

None. Static prompts and answers.

Evaluation style
Automatic reference match, Static Q&A
Environment summary
Not published

Model requirements

Required conditions decide applicability. Relevant ones describe what the benchmark exercises and decide nothing.

Required · decides applicability

Whole benchmark
Text (input)Text (output)Complex reasoning

Relevant · informational

Explicit reasoningGeneral purpose modelsReasoning models

CTXDEX models

13 of the 58 active, preview, experimental models meet this benchmark’s recorded requirements, at some scope. Applicable means the requirements are met, not that the model was evaluated.

View all 13 applicable models →
Applicable · full
13
Applicable · components
0
Applicable · scenarios
0
Conditionally applicable
0
Not recorded
45

Counted over 58 models in the default lifecycle scope (active, preview, experimental).

Every required condition, for the whole benchmark, is recorded as supported. Each line is one recorded condition and why it counts.

  • Ctxdex Chintana 1 Large
    Ctxdex Efficient Reasoning
    Full benchmark

    Every one of the 3 required conditions is recorded as supported.

    • MODALITY:INPUT:TEXTthe catalogue records SUPPORTED for TEXT (input)
    • MODALITY:OUTPUT:TEXTthe catalogue records SUPPORTED for TEXT (output)
    • MODEL_TASK:COMPLEX_REASONINGthe catalogue records SUPPORTED for COMPLEX_REASONING
  • Ctxdex Chintana 1 Mini
    Ctxdex Efficient Reasoning
    Full benchmark

    Every one of the 3 required conditions is recorded as supported.

    • MODALITY:INPUT:TEXTthe catalogue records SUPPORTED for TEXT (input)
    • MODALITY:OUTPUT:TEXTthe catalogue records SUPPORTED for TEXT (output)
    • MODEL_TASK:COMPLEX_REASONINGthe catalogue records SUPPORTED for COMPLEX_REASONING
Preview holds 12 of 13. View all →

Applicability/relevance ordering only; never a performance ranking.

Scale

  • 448
    Question
    Main · Exact
  • 546
    Question
    Extended · Exact
  • 198
    Question
    Diamond · Exact

Data and access

Dataset
Open
Evaluation code
Open source
Unknown
Leaderboard, Peer review, Maintenance

Coverage

Language
English (primary)
Coverage summary
Not published

Limitations

None recorded

Lineage

Family
FamilyGPQA
Related
Superset of BenchmarkGPQA Diamond
Other definitions in family
GPQA Diamond Active
Changes

None recorded

Sources

Freshness

Content version
1.0
Last reviewed
2026-09-22
Refresh model
Static
Time sensitivity
Low
Benchmark data
c40cccac878af5d0

13 contract fields are empty for every benchmark in this release and are not shown: applicability groups, conditional requirements, feature requirements, model relevance domains, required capabilities, openness summary, reference artifacts, interaction protocols, tool protocols, benchmark last major refresh at, short name, target expertise level, target population.