BLXBenchBLXBench UI
blxbench

Benchmark

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
BLXBenchBLXBench UI
blxbench

Benchmark

Suite

Misc

DocsOur TestsPassSponsor / Partnership
DocsOur TestsPassSponsor / Partnership
  1. Home
  2. Our Tests
  3. Halluc-Complexity-Graph-Bfs
blxbench

Test fixture

Halluc-Complexity-Graph-Bfs

Hallucinationv2 — Resiliencehardscorer: rubric_json_metrics

Grounded answers under adversarial or missing-context prompts.

How it is scored

The model receives the prompt (and optional system message). The run uses scorer rubric_json_metrics with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.

User prompt
Return JSON only with keys answer, supported_facts, uncertainty. For BFS over adjacency lists with V vertices and E edges, state time complexity and avoid claiming O(V squared) for all graphs.
Scorer config
{
  "metrics": {
    "accuracy": {
      "checks": [
        {
          "contains": [
            "O(V+E)"
          ]
        },
        {
          "contains": [
            "adjacency lists"
          ]
        },
        {
          "contains": [
            "BFS"
          ]
        }
      ]
    },
    "fabricated": {
      "checks": [
        {
          "contains": [
            "not O(V squared)"
          ]
        },
        {
          "contains": [
            "vertices"
          ]
        },
        {
          "contains": [
            "edges"
          ]
        }
      ]
    }
  }
}
Run parameters

temperature

0

max_tokens

460

timeout (s)

120

type

scored

file

halluc-complexity-graph-bfs.json

← PreviousHalluc-Compl-Regex-Compile
|
Next →Halluc-Complexity-Recursive-Memo

BLXBench

Community driven leaderboardPublic benchmark runner — run in your environment, share results with the community.

© 2026 BLXBench by bitslix.com

ProvenanceAggregated from user runs
Scope43 / 11 / 490
Latestrun_7730ad / 459 / $0.00
TermsPrivacy