Benchmark plan / wildbench

WildBench

preference · instruct · en

planned · No sub-1B cohort score yet. Planning cost W; actual GPU time is not measured.

Judge cost and bias must be measured; not human preference ground truth.

Before scheduling

Pin dataset revision, split and item IDs; validate the native-model adapter; set context and generation budgets; freeze prompts, decoding, scoring and any grader/environment. Report every compatible system in the same scope. Long-context or gated data may require further preparation.

Presets: Optional additional coverage. Qualified detail-page visits affect planning priority, not automatic budget expansion.

Ontology record

{
  "number": 47,
  "benchmark_id": "wildbench",
  "name": "WildBench",
  "benchmark_family": "wildbench",
  "task_ids": [
    "preference"
  ],
  "group": "trust-preference-multilingual",
  "source": "https://github.com/allenai/WildBench",
  "liquid": [],
  "presets": [],
  "languages": [
    "en"
  ],
  "base_or_instruct": "instruct",
  "metric": "judge_score",
  "direction": "max",
  "dataset_revision": null,
  "split": null,
  "item_ids": null,
  "protocol_id": null,
  "generation_and_context_budget": {
    "max_input_tokens": null,
    "max_output_tokens": null,
    "sample_count": null
  },
  "grader_or_environment": "Pinned external judge required",
  "measured_cost": null,
  "planning_cost": "W",
  "status": "planned",
  "note": "Judge cost and bias must be measured; not human preference ground truth.",
  "existing_adapter_task": null,
  "comparison_scope": "No sub-1B cohort result for this catalogue entry yet",
  "execution_tier": 4,
  "execution_priority_reason": "Expensive or ambitious extension",
  "execution_order": 147,
  "visits_30d": 0,
  "demand": 0,
  "priority": 0
}