Model evidence / legacy era
Recorded agent setup
Gemini Flash (latest alias)
Effort: default (unverified) · legacy era
Harness: Gemini CLI
Effort mode was not recorded; no equivalence to a named effort is assumed.
Task selection is incompletely recorded; catalog-wide generalization is unsupported.
17.8%macro pass estimate
3eligible benchmark task versions
13valid runs on those tasks
3HARNESS_ERROR · excluded in scope
Macro: 17.8% [0.0%, 48.9%] · Micro: 2/13 · 15.4% [4.3%, 42.2%]. Latest nondefective task versions, each with ≥3 valid runs; a macro needs ≥3 tasks. The model’s measured subset differs from other rows.
Domain results
| Domain | Tasks / runs | Macro [95% bootstrap] | Micro [95% Wilson] | Calibration |
|---|---|---|---|---|
| Cloud operations | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Data processing / data science | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| DeepSWE (long-horizon SWE) | 3 / 13 | 17.8% [0.0%, 48.9%] | 2/13 · 15.4% [4.3%, 42.2%] | Limited coverage |
| Electrical engineering (RTL) | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Games | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Machine learning | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Mechanical engineering | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Media | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Operations | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Other / uncategorised | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| SWE-Marathon | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Science / STEM | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Scientific computing | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Security / cyber | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Snorkel-reviewed tasks (category unknown) | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
| Software engineering | 0 / 0 | Insufficient task coverage | 0/0 | Limited coverage |
Resource coverage
Valid runs on nondefective benchmark versions. Missing values are excluded, never counted as zero. Medians are descriptive and can reflect different task difficulty and harness behavior.
| Recorded resource | Median | Observed / eligible runs |
|---|---|---|
| Recorded tokens | — | 0 / 15 |
| Cost (USD) | — | 0 / 15 |
| Agent turns | — | 0 / 15 |
| Duration (seconds) | — | 0 / 15 |
Task-level evidence
Includes excluded and superseded versions for inspection; only the chosen nondefective versions enter aggregate results. Each task links to the exact runs and their diagnostic provenance.
| Task / version | Domain | Verifier outcome [95% Wilson] | Tier / aggregate scope |
|---|---|---|---|
| syncrope/marked-commonmark-strictVersion 1 | DeepSWE (long-horizon SWE) | 1/5 · 20.0% [3.6%, 62.4%] | saturatedBenchmark version |
| oxigraph-write-policy-ec68e3dVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | uncalibratedBenchmark version |
| path-to-regexp-route-fragments-bd12a33Version 1 | DeepSWE (long-horizon SWE) | 0/0 | saturatedBenchmark version |
| syncrope/babel-messageformat2Version 1 | DeepSWE (long-horizon SWE) | 0/1 | hardBenchmark version |
| syncrope/echo-http-signaturesVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | legacy-onlyBenchmark version |
| syncrope/ammonia-sanitizer-apiVersion 1 | DeepSWE (long-horizon SWE) | 0/1 | saturatedBenchmark version |
| syncrope/networkx-graphml-fullVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | hardExcluded / other version |
| gopher-lua-exact-integers-75f4976Version 1 | DeepSWE (long-horizon SWE) | 0/0 | saturatedBenchmark version |
| syncrope/uniseg-bidi-uax9Version 1 | DeepSWE (long-horizon SWE) | 0/5 · 0.0% [0.0%, 43.4%] | mediumBenchmark version |
| syncrope/paramiko-knownhosts-engineVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | hardExcluded / other version |
| syncrope/bibtexparser-biblatex-modelVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | legacy-onlyBenchmark version |
| syncrope/spdx-matching-guidelinesVersion 1 | DeepSWE (long-horizon SWE) | 1/3 · 33.3% [6.1%, 79.2%] · preliminary | contested/defectiveExcluded / other version |
| syncrope/oxigraph-shacl-coreVersion 1 | DeepSWE (long-horizon SWE) | 0/5 · 0.0% [0.0%, 43.4%] | mediumExcluded / other version |
| syncrope/iconv-lite-whatwg-modeVersion 1 | DeepSWE (long-horizon SWE) | 1/3 · 33.3% [6.1%, 79.2%] · preliminary | mediumBenchmark version |
| paramiko-knownhosts-engineVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | saturatedBenchmark version |
| syncrope/jimp-exif-engineVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | legacy-onlyBenchmark version |
| syncrope/linkedom-range-selectionVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | legacy-onlyBenchmark version |
| syncrope/goldmark-cmark-sourceposVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | uncalibratedBenchmark version |
| syncrope/gopher-lua-54-semanticsVersion 1 | DeepSWE (long-horizon SWE) | 0/0 | hardExcluded / other version |
| syncrope/path-to-regexp-urlpatternVersion 1 | DeepSWE (long-horizon SWE) | 2/4 · 50.0% [15.0%, 85.0%] · preliminary | mediumExcluded / other version |
| hello-worldVersion 1 | Other / uncategorised | 0/0 | uncalibratedBenchmark version |