Benchmark definition
SWE-bench Science
Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.
About
- Description
- SWE-bench Science
- What it measures
- SWE-bench Science
- Comparison guidance
- Not published
- Intended difficulty
- Not published
Not recorded for this benchmark: what it does not measure, why it matters, motivation, gap addressed.
Classification
- Categories
- Software Engineering
- Domains
None recorded
- Evaluation style
None recorded
Structure
5 scenarios. Applicability can differ between them.
Scenarios
- Issue Driven
- Expert Exploratory
- Engineering Integration
- Scientific Guidance Present
- Scientific Guidance Ablated
Tasks
Metrics
What a result on this benchmark would be reported as. ctxdex does not carry results.
| Metric | Role | Direction | Unit |
|---|---|---|---|
Resolved Rate Metric code used by canonical Batch-2 benchmark definitions; exact benchmark-specific semantics remain in benchmark_metric parameters/methodology. | Primary | Higher is better | Percent |
Test Pass Rate Canonical Batch-2 metric code TEST_PASS_RATE; benchmark-specific formula/parameters remain on benchmark_metric and methodology records. | Secondary | Higher is better | Percent |
Methodology
None recorded
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
- Not recorded
- Environment summary
- Not published
Model requirements
Required conditions decide applicability. Relevant ones describe what the benchmark exercises and decide nothing.
Required · decides applicability
Relevant · informational
CTXDEX models
6 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 6 applicable models →- Applicable · full
- 6
- Applicable · components
- 0
- Applicable · scenarios
- 0
- Conditionally applicable
- 0
- Not recorded
- 52
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.
Every one of the 1 required conditions is recorded as supported.
MODEL_TASK:AGENTIC_SOFTWARE_ENGINEERINGthe catalogue records SUPPORTED for AGENTIC_SOFTWARE_ENGINEERING
Every one of the 1 required conditions is recorded as supported.
MODEL_TASK:AGENTIC_SOFTWARE_ENGINEERINGthe catalogue records SUPPORTED for AGENTIC_SOFTWARE_ENGINEERING
Applicability/relevance ordering only; never a performance ranking.
Scale
- 96Default unrestrictedTotal · Exact
- 98RepositoryTotal · Exact
- 23RestrictedTotal · Exact
- 91Science knowledge ablationTotal · Exact
- 20DomainTotal · Exact
- {"ENGINEERING_INTEGRATION":18,"EXPERT_EXPLORATORY":49,"ISSUE_DRIVEN":52}TaskTotal · Exact
- 119TaskTotal · Exact
Data and access
Coverage
- Languages, regions
None recorded
- Coverage summary
- Not published
Limitations
None recorded
Lineage
- Family
- FamilySwe Bench Science
- Related
- Changes
None recorded
Sources
None recorded
Freshness
- Content version
- B2-1.0
- Last reviewed
- 2026-09-23
- Refresh model
- Unknown
- Time sensitivity
- Unknown
- 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.