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. Speed-Test-Plan
blxbench

Test fixture

Speed-Test-Plan

Speedv2 — Resiliencemediumscorer: rubric_json_metrics

Throughput and TTFT-focused generation tasks.

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 benchmark, title, sections, done. Set benchmark to "speed", title to "Test Plan", and done to true. Write a concise test plan for a billing export feature with 5 sections and 5 bullets each.
Scorer config
{
  "metrics": {
    "complete": {
      "checks": [
        {
          "contains": [
            "speed"
          ]
        },
        {
          "contains": [
            "done"
          ]
        },
        {
          "contains": [
            "test"
          ]
        }
      ]
    }
  }
}
Run parameters

temperature

0

max_tokens

620

timeout (s)

120

type

throughput

file

speed-test-plan.json

← PreviousSpeed-Test-Names
|
Next →Speed-Typescript-Utils

BLXBench

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

© 2026 BLXBench by bitslix.com

ProvenanceAggregated from user runs
Scope40 / 11 / 490
Latestrun_f78b01 / 459 / $18.57
TermsPrivacy