Benchmark Registry

DeepSWE

Updated

Cite

Fill in the access date before citing.

Plain text 

Benchmark Registry. DeepSWE 1.1 — mini-swe-agent benchmark results. Benchmark identifier: deep-swe/1.1-mini-swe-agent. https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX 

@misc{br_deep_swe_1_1_mini_swe_agent,
  title = {DeepSWE 1.1 — mini-swe-agent benchmark results},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent},
  urldate = {YYYY-MM-DD},
  note = {Benchmark identifier: deep-swe/1.1-mini-swe-agent; data license: CC BY 4.0; access date to be filled by the reader}
}
Report an issue
Benchmark
DeepSWE
Evaluated by
DataCurve
Release date
June 15, 2026
Version
DeepSWE 1.1 — mini-swe-agent
Metric
DeepSWE Pass@1

Results

4 results

ProviderModelScoreSourceRegistry No.
Google (DeepMind)Gemini 4 Argon (highest thinking settings)77.9%deepmind.googleDeepSWE Pass@1Reported Google DeepMindReport an issue
Cite

Fill in the access date before citing.

Plain text 

Benchmark Registry. Gemini 4 Argon: DeepSWE 1.1 — mini-swe-agent, 77.9% (highest thinking settings). Registry No. 30011; Record No. 1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919. https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919#BR-1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX 

@misc{br_1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919,
  title = {Gemini 4 Argon: DeepSWE 1.1 — mini-swe-agent, 77.9\% (highest thinking settings)},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history\&result=1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919\#BR-1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919},
  urldate = {YYYY-MM-DD},
  note = {Registry No. 30011; Record No. 1decceb85b196ca5b414edec7681bf381e53550ad4c91d4c686a8b4ceabd5919; data license: CC BY 4.0; access date to be filled by the reader}
}

Permalink to this record

Badge for this model's latest reported score in the benchmark family; it may differ from this record.

Markdown 

![Gemini 4 Argon: DeepSWE](https://benchmarkregistry.org/badge/30011/deep-swe.svg)

HTML 

<img src="https://benchmarkregistry.org/badge/30011/deep-swe.svg" alt="Gemini 4 Argon: DeepSWE" height="24">
30011
Meta AI (originally Facebook AI Research)Muse Spark 1.2 (xhigh)55.0%research.meta.aiDeepSWE Pass@1Reported DataCurveReport an issue
Cite

Fill in the access date before citing.

Plain text 

Benchmark Registry. Muse Spark 1.2: DeepSWE 1.1 — mini-swe-agent, 55.0% (xhigh). Registry No. 80003; Record No. 5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae. https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae#BR-5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX 

@misc{br_5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae,
  title = {Muse Spark 1.2: DeepSWE 1.1 — mini-swe-agent, 55.0\% (xhigh)},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history\&result=5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae\#BR-5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae},
  urldate = {YYYY-MM-DD},
  note = {Registry No. 80003; Record No. 5ef58f90665fd52308dc3b6aa640272faaffebf480875ca48edb776dc482baae; data license: CC BY 4.0; access date to be filled by the reader}
}

Permalink to this record

Badge for this model's latest reported score in the benchmark family; it may differ from this record.

Markdown 

![Muse Spark 1.2: DeepSWE](https://benchmarkregistry.org/badge/80003/deep-swe.svg)

HTML 

<img src="https://benchmarkregistry.org/badge/80003/deep-swe.svg" alt="Muse Spark 1.2: DeepSWE" height="24">
80003
Meta AI (originally Facebook AI Research)Muse Spark 1.3 (max)75.4%dev.meta.aiDeepSWE Pass@1Reported MetaReport an issue
Cite

Fill in the access date before citing.

Plain text 

Benchmark Registry. Muse Spark 1.3: DeepSWE 1.1 — mini-swe-agent, 75.4% (max). Registry No. 80005; Record No. 80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3. https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3#BR-80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX 

@misc{br_80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3,
  title = {Muse Spark 1.3: DeepSWE 1.1 — mini-swe-agent, 75.4\% (max)},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history\&result=80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3\#BR-80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3},
  urldate = {YYYY-MM-DD},
  note = {Registry No. 80005; Record No. 80504116937e45a40c7307698163c7078c547ce1252c54b62b6e06521a6b40b3; data license: CC BY 4.0; access date to be filled by the reader}
}

Permalink to this record

Badge for this model's latest reported score in the benchmark family; it may differ from this record.

Markdown 

![Muse Spark 1.3: DeepSWE](https://benchmarkregistry.org/badge/80005/deep-swe.svg)

HTML 

<img src="https://benchmarkregistry.org/badge/80005/deep-swe.svg" alt="Muse Spark 1.3: DeepSWE" height="24">
80005
Meta AI (originally Facebook AI Research)Muse Spark 1.1 (xhigh)53.3%dev.meta.aiDeepSWE Pass@1Reported MetaReport an issue
Cite

Fill in the access date before citing.

Plain text 

Benchmark Registry. Muse Spark 1.1: DeepSWE 1.1 — mini-swe-agent, 53.3% (xhigh). Registry No. 80002; Record No. 2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09. https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history&result=2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09#BR-2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09. Accessed [YYYY-MM-DD]. Data license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Attribution: Benchmark Registry, a project of Densa Labs — https://benchmarkregistry.org/ (CC BY 4.0). Include the cited record URL and identify any changes.

BibTeX 

@misc{br_2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09,
  title = {Muse Spark 1.1: DeepSWE 1.1 — mini-swe-agent, 53.3\% (xhigh)},
  publisher = {Benchmark Registry},
  url = {https://benchmarkregistry.org/benchmarks/deep-swe/1.1-mini-swe-agent?view=history\&result=2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09\#BR-2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09},
  urldate = {YYYY-MM-DD},
  note = {Registry No. 80002; Record No. 2451b2517dc563b1681415ecd476f0b874d7ec38aa8a90cb8141ca0be351af09; data license: CC BY 4.0; access date to be filled by the reader}
}

Permalink to this record

Badge for this model's latest reported score in the benchmark family; it may differ from this record.

Markdown 

![Muse Spark 1.1: DeepSWE](https://benchmarkregistry.org/badge/80002/deep-swe.svg)

HTML 

<img src="https://benchmarkregistry.org/badge/80002/deep-swe.svg" alt="Muse Spark 1.1: DeepSWE" height="24">
80002