{
  "title": "DeepSeek V4.1 Flash: 1017 compared with the original",
  "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md",
  "original_source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/314113f8a7dadb388215396ba5fbee2c610a04d6/README.md",
  "releases": {
    "new": "DeepSeek-V4.1-Flash-1017",
    "original": "DeepSeek-V4.1-Flash"
  },
  "config_sha256": "8be45ce0476004a3f529fd896115a4a2e800a129ad2d3ec05b16050f52e21879",
  "inference_config_sha256": "2e84f45cf1dac8c7fcbb200e96667d4b913275690668ed496f24c7747207a809",
  "revisions": {
    "new": "1bae0e1088993b9b82de08f59de5be5a34e42170",
    "original": "314113f8a7dadb388215396ba5fbee2c610a04d6"
  },
  "benchmarks": [
    {"id":"hle","name":"HLE without tools","original":36.8,"new":42.6,"note":"Text-only HLE subset: 39.1 original, 44.0 in 1017. The main chart uses the full HLE without-tools pair."},
    {"id":"terminal","name":"Terminal-Bench 4.0","original":31.2,"new":42.3,"note":"The publisher reports this result using the Claude Code harness."},
    {"id":"deepswe","name":"DeepSWE v1.1","original":74.2,"new":77.0,"note":"The publisher reports this result using the Mini-SWE-V2 harness."},
    {"id":"program","name":"ProgramBench","original":20.3,"new":29.1},
    {"id":"nl2repo","name":"NL2Repo-Bench","original":65.4,"new":68.2},
    {"id":"automation","name":"Automation-Bench v1.0.6","original":54.8,"new":60.5},
    {"id":"agents","name":"Agents’ Last Exam","original":31.8,"new":35.4},
    {"id":"apex","name":"Apex Bench v1.1","original":64.6,"new":72.1},
    {"id":"chartography","name":"Chartography with tools","original":78.9,"new":83.0,"with_tools":true},
    {"id":"babyvision","name":"BabyVision with tools","original":89.6,"new":92.5,"with_tools":true},
    {"id":"zerobench","name":"ZeroBench-main with tools","original":49.0,"new":51.0,"with_tools":true}
  ]
}