{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "0228b7b1-9f32-4d34-8afa-43e873cc2f8f",
  "run_id": "13fdf49df903ef19c383a9bd5a71a59c",
  "created_at_unix_ms": 1789849974885,
  "submitted_by": "prabod",
  "model": {
    "canonical_id": "openai/gpt-oss-120b",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-11T12:18:35.929Z",
    "name": "gpt-oss-120b-Q4",
    "architecture": "gpt_oss",
    "quantization": "base_q4",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "basecompute/gpt-oss-120b",
      "revision": "f2faf6c856270dab08d35a9627d0dea89bfeae86",
      "path": "gpt-oss-120b-Q4.base",
      "sha256": "540642b331aa4f4ebd103a649fc53f5c8b78f1d453f1c12a3121596fa3b582d3",
      "format": "base",
      "quantization_namespace": "basert",
      "quantization_scheme": "base_q4"
    }
  },
  "runtime": {
    "name": "basert",
    "version": "0.2.6"
  },
  "benchmark": {
    "mode": "text",
    "chip": "NVIDIA GB10",
    "backend": "cuda",
    "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": 1374.6899765861701
        },
        {
          "tokens": 256,
          "tokens_per_second": 2052.8837630580542
        },
        {
          "tokens": 512,
          "tokens_per_second": 2619.1880149737194
        },
        {
          "tokens": 1024,
          "tokens_per_second": 2970.566832509121
        },
        {
          "tokens": 2048,
          "tokens_per_second": 2992.1827340577825
        },
        {
          "tokens": 4096,
          "tokens_per_second": 2720.478643742063
        },
        {
          "tokens": 8192,
          "tokens_per_second": 2217.569912488801
        },
        {
          "tokens": 16384,
          "tokens_per_second": 1615.4350107235466
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 39.70668540879797
      }
    }
  }
}