{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "9184d64c-27c3-4211-b1fe-425c1ed3e210",
  "run_id": "e5acbc4b2ee242a9b73899e0724dc20a",
  "created_at_unix_ms": 1789864466254,
  "submitted_by": "prabod",
  "model": {
    "canonical_id": "openai/gpt-oss-20b",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-11T12:18:35.929Z",
    "name": "gpt-oss-20b-Q4",
    "architecture": "gpt_oss",
    "quantization": "base_q4",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "basecompute/gpt-oss-20b",
      "revision": "6dc70937996ff2cf3bb552046f693018b43f7cc8",
      "path": "gpt-oss-20b-Q4.base",
      "sha256": "6b7ae00571be1b9d4e5204c34e9fe22c19ee69c5dd6e51d32900cf8d41091c7f",
      "format": "base",
      "quantization_namespace": "basert",
      "quantization_scheme": "base_q4"
    }
  },
  "runtime": {
    "name": "basert",
    "version": "0.2.6"
  },
  "benchmark": {
    "mode": "text",
    "chip": "Apple M4 Max",
    "backend": "metal",
    "protocol": {
      "report_schema": "computearena-benchmark/1",
      "benchmark_schema": "basert-benchmark-harness/1",
      "telemetry_schema": "basert-telemetry/4",
      "throughput_schema": "computearena-throughput/3",
      "comparable": true,
      "context_isolation": "headline_then_per_prefill",
      "execution_layout": "headline_then_prefill_processes",
      "model_load_in_timing": false,
      "decode_initial_context_tokens": 1,
      "conditioning_schema": "basert-conditioning/1",
      "conditioning_mode": "warmup_only",
      "cooldown_enabled": false
    },
    "parameters": {
      "context_tokens": 16384,
      "decode_context_tokens": 1
    },
    "throughput": {
      "prefill": [
        {
          "tokens": 128,
          "tokens_per_second": 1229.5673349039193
        },
        {
          "tokens": 256,
          "tokens_per_second": 1514.735660853643
        },
        {
          "tokens": 512,
          "tokens_per_second": 1708.9035895901613
        },
        {
          "tokens": 1024,
          "tokens_per_second": 1801.8501872759177
        },
        {
          "tokens": 2048,
          "tokens_per_second": 1801.2828399014368
        },
        {
          "tokens": 4096,
          "tokens_per_second": 1714.958989720834
        },
        {
          "tokens": 8192,
          "tokens_per_second": 1506.1034631035045
        },
        {
          "tokens": 16384,
          "tokens_per_second": 1196.7310060352636
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 160.50633435514382
      }
    }
  }
}