nightly-eval · sim-small-v3 simulated

Completed   dataset /home/evalpipe/demo_dataset.jsonl   started 2026-07-13 01:08:35 UTC   run id 6464d1dcf5ee496faf3c724c7176964c  ·  Download CSV · JSON

Full results for this single run: the headline scores, how answers were spread out, where the model was strong or weak, and every question with the model's answer.

Pass rate
62.5%
Share of questions answered well enough to pass every check.
95% CI 47.0% – 75.8% (the true rate likely sits in this range)
Mean score
0.819
Average answer quality on a 0–1 scale, across all metrics.
40 questions · 0 error(s)
Latency
26 ms
How long the model took to answer — typical (p50) and near‑worst (p95).
p50 · p95 36 ms
Estimated cost
$0.5430
Rough API cost for this run, based on tokens used.
token-based estimate

Score distribution

How many questions landed in each quality band (0 = wrong, 1 = perfect). Most bars bunched on the right means the model answered well overall.

View data table
Score binItems
0.0-0.10
0.1-0.20
0.2-0.30
0.3-0.43
0.4-0.55
0.5-0.60
0.6-0.72
0.7-0.84
0.8-0.90
0.9-1.026

Mean score by evaluator

How each type of check graded this run (0–1). A short bar flags the quality dimension the model is weakest on.

View data table
EvaluatorMean score
exact_match0.650
llm_judge_correctness0.892
safety1.000
semantic_similarity0.772
token_f10.781

Where it's strong or weak

Pass rate split by difficulty, so a good overall score can't hide a weak spot (e.g. "95% on easy, 20% on hard").

View data table
Difficulty Items Pass rate 95% CI Mean score
easy 22 59.1% 38.7–76.7% 0.816
medium 17 64.7% 41.3–82.7% 0.813
hard 1 100.0% 20.7–100.0% 0.980

Every question

Each question with its outcome, score, and the model's answer. Use Failed to jump straight to what went wrong; open Details on a row to see the prompt, expected answer, and per‑check scores.

Item Outcome Score Latency Output
qa-003 Fail 0.400 35 ms The answer depends on several factors that are not specified here.
Details

Prompt

Answer the question accurately and concisely. Question: Who wrote the play Romeo and Juliet?

Expected

Romeo and Juliet was written by William Shakespeare.

Model output

The answer depends on several factors that are not specified here.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.000
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-005 Fail 0.705 23 ms The largest ocean on Earth.
Details

Prompt

Answer the question accurately and concisely. Question: What is the largest ocean on Earth?

Expected

The Pacific Ocean is the largest ocean on Earth.

Model output

The largest ocean on Earth.

  • exact_match Fail 0.000
  • token_f1 Pass 0.727
  • semantic_similarity Pass 0.800
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-006 Fail 0.654 33 ms There seven continents Earth.
Details

Prompt

Answer the question accurately and concisely. Question: How many continents are there on Earth?

Expected

There are seven continents on Earth.

Model output

There seven continents Earth.

  • exact_match Fail 0.000
  • token_f1 Pass 0.800
  • semantic_similarity Pass 0.570
  • llm_judge_correctness Pass 0.900 judge score 9/10
  • safety Pass 1.000 no blocked terms present
qa-012 Fail 0.920 15 ms The Nile is generally considered the longest river in the world.
Details

Prompt

Answer the question accurately and concisely. Question: What is the longest river in the world?

Expected

The Nile is generally considered the longest river in the world.

Model output

The Nile is generally considered the longest river in the world.

  • exact_match Pass 1.000
  • token_f1 Pass 1.000
  • semantic_similarity Pass 1.000
  • llm_judge_correctness Fail 0.600 judge score 6/10
  • safety Pass 1.000 no blocked terms present
qa-013 Fail 0.360 13 ms The answer depends on several factors that are not specified here.
Details

Prompt

Answer the question accurately and concisely. Question: How many sides does a hexagon have?

Expected

A hexagon has six sides.

Model output

The answer depends on several factors that are not specified here.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.000
  • llm_judge_correctness Pass 0.800 judge score 8/10
  • safety Pass 1.000 no blocked terms present
qa-017 Fail 0.371 14 ms The answer depends on several factors that are not specified here.
Details

Prompt

Answer the question accurately and concisely. Question: Who developed the theory of general relativity?

Expected

Albert Einstein developed the theory of general relativity.

Model output

The answer depends on several factors that are not specified here.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.056
  • llm_judge_correctness Pass 0.800 judge score 8/10
  • safety Pass 1.000 no blocked terms present
qa-019 Fail 0.436 32 ms The answer depends on several factors that are not specified here.
Details

Prompt

Answer the question accurately and concisely. Question: How many minutes are there in two hours?

Expected

There are 120 minutes in two hours.

Model output

The answer depends on several factors that are not specified here.

  • exact_match Fail 0.000
  • token_f1 Fail 0.118
  • semantic_similarity Fail 0.061
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-020 Fail 0.722 31 ms Portuguese the primary language spoken in
Details

Prompt

Answer the question accurately and concisely. Question: What is the primary language spoken in Brazil?

Expected

Portuguese is the primary language spoken in Brazil.

Model output

Portuguese the primary language spoken in

  • exact_match Fail 0.000
  • token_f1 Pass 0.833
  • semantic_similarity Pass 0.778
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-023 Fail 0.376 16 ms That is outside the scope of what I can determine from the prompt.
Details

Prompt

Answer the question accurately and concisely. Question: In which year did the Apollo 11 mission land humans on the Moon?

Expected

Apollo 11 landed humans on the Moon in 1969.

Model output

That is outside the scope of what I can determine from the prompt.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.081
  • llm_judge_correctness Pass 0.800 judge score 8/10
  • safety Pass 1.000 no blocked terms present
qa-026 Fail 0.692 16 ms Pride Prejudice was written by Austen.
Details

Prompt

Answer the question accurately and concisely. Question: Who wrote the novel Pride and Prejudice?

Expected

Pride and Prejudice was written by Jane Austen.

Model output

Pride Prejudice was written by Austen.

  • exact_match Fail 0.000
  • token_f1 Pass 0.857
  • semantic_similarity Pass 0.701
  • llm_judge_correctness Pass 0.900 judge score 9/10
  • safety Pass 1.000 no blocked terms present
qa-030 Fail 0.400 28 ms The answer depends on several factors that are not specified here.
Details

Prompt

Answer the question accurately and concisely. Question: Which metal is liquid at room temperature?

Expected

Mercury is liquid at room temperature.

Model output

The answer depends on several factors that are not specified here.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.000
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-033 Fail 0.466 36 ms That is outside the scope of what I can determine from the prompt.
Details

Prompt

Answer the question accurately and concisely. Question: What is the fastest land animal?

Expected

The cheetah is the fastest land animal.

Model output

That is outside the scope of what I can determine from the prompt.

  • exact_match Fail 0.000
  • token_f1 Fail 0.125
  • semantic_similarity Fail 0.204
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-035 Fail 0.400 29 ms I do not have enough information to answer that question.
Details

Prompt

Answer the question accurately and concisely. Question: What is the chemical formula for table salt?

Expected

The chemical formula for table salt is NaCl.

Model output

I do not have enough information to answer that question.

  • exact_match Fail 0.000
  • token_f1 Fail 0.000
  • semantic_similarity Fail 0.000
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-037 Fail 0.723 16 ms A has seven colors.
Details

Prompt

Answer the question accurately and concisely. Question: How many colors are there in a rainbow?

Expected

A rainbow has seven colors.

Model output

A has seven colors.

  • exact_match Fail 0.000
  • token_f1 Pass 0.857
  • semantic_similarity Pass 0.756
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present
qa-039 Fail 0.755 33 ms Mercury is the planet closest the Sun.
Details

Prompt

Answer the question accurately and concisely. Question: Which planet is closest to the Sun?

Expected

Mercury is the planet closest to the Sun.

Model output

Mercury is the planet closest the Sun.

  • exact_match Fail 0.000
  • token_f1 Pass 0.909
  • semantic_similarity Pass 0.867
  • llm_judge_correctness Pass 1.000 judge score 10/10
  • safety Pass 1.000 no blocked terms present