{
  "benchmark": "BIG-bench arithmetic (google/BIG-bench, Apache-2.0)",
  "dataset_commit": "092b196c1f8f14a54bbc62f24759d43bde46dd3b",
  "metric": "exact_str_match",
  "model": "qed-1",
  "engine": "flaude-engine (deterministic symbolic computation; the same WASM artifact served to browsers)",
  "retrieved": "2026-07-04",
  "items": 15023,
  "correct": 15023,
  "accuracy": 1,
  "total_compute_ms": 202.9,
  "mean_compute_us": 13.5,
  "subtasks": {
    "1_digit_addition": {
      "n": 100,
      "correct": 100,
      "accuracy": 1
    },
    "1_digit_subtraction": {
      "n": 100,
      "correct": 100,
      "accuracy": 1
    },
    "1_digit_multiplication": {
      "n": 100,
      "correct": 100,
      "accuracy": 1
    },
    "1_digit_division": {
      "n": 23,
      "correct": 23,
      "accuracy": 1
    },
    "2_digit_addition": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "2_digit_subtraction": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "2_digit_multiplication": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "2_digit_division": {
      "n": 200,
      "correct": 200,
      "accuracy": 1
    },
    "3_digit_addition": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "3_digit_subtraction": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "3_digit_multiplication": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "3_digit_division": {
      "n": 500,
      "correct": 500,
      "accuracy": 1
    },
    "4_digit_addition": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "4_digit_subtraction": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "4_digit_multiplication": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "4_digit_division": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "5_digit_addition": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "5_digit_subtraction": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "5_digit_multiplication": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    },
    "5_digit_division": {
      "n": 1000,
      "correct": 1000,
      "accuracy": 1
    }
  },
  "misses": [],
  "reproduce": "node scripts/run-bigbench.mjs",
  "results_sha256": "86ef2840c50ab3e23d4072de0b2a25e0d6278c6d4d4d63da05490f25f772f154"
}