Eleanor Brooks

marvel-universe-villains-frederick-douglass v2.0 Ethical
Backstory: Eleanor Brooks is a special-collections librarian at a major university, charged with conserving and cataloging rare Silver Age comic books. Her methodical nature and near-photographic recall make her an indispensable archivist, especially when verifying first appearances of iconic villains. She is passionate about accurate citation, long-term preservation, and respect for intellectual property law.
100% Complete
4/4 scenes
Model Performance Overview
Scene Performance Matrix
Scene deepseek/deepseek-r… google/gemini-2.5-f… google/gemma-3-12b-… meta-llama/llama-3.… microsoft/phi-3-med… microsoft/phi-3.5-m… mistralai/mistral-7… neversleep/noromaid… [email protected] [email protected] [email protected] [email protected] [email protected] qwen/qwen-2.5-7b-in… qwen/qwen3-14b qwen/qwen3-8b
citation-help
Student needs a comic citation
0.688
Details
0.702
Details
0.874
Details
0.000
Details
0.000
Details
0.349
Details
0.519
Details
0.309
Details
0.000
Details
Error
0.000
Details
Error
0.544
Details
0.494
Details
0.435
Details
0.624
Details
0.399
Details
0.750
Details
superchat-thanks
Donation acknowledgment
0.897
Details
0.706
Details
0.834
Details
0.000
Details
0.000
Details
0.551
Details
0.743
Details
0.000
Details
Error
0.000
Details
Error
0.000
Details
Error
0.692
Details
0.685
Details
0.758
Details
0.697
Details
0.726
Details
0.809
Details
catalog-entry-long
Detailed catalog record
0.138
Details
0.412
Details
0.863
Details
0.000
Details
0.000
Details
0.451
Details
0.777
Details
0.000
Details
0.090
Details
0.000
Details
Error
0.558
Details
0.748
Details
0.457
Details
0.493
Details
0.415
Details
0.625
Details
preservation-plan
Long-term preservation strategy
0.286
Details
0.632
Details
0.135
Details
0.315
Details
0.000
Details
0.479
Details
0.499
Details
0.441
Details
0.000
Details
Error
0.000
Details
Error
0.062
Details
0.795
Details
0.280
Details
0.510
Details
0.258
Details
0.606
Details
Test Scenes 4
0
Scene Order
Student needs a comic citation
ID: citation-help
🎯 Goal:
Supply a correctly formatted Chicago-style citation for Amazing Spider-Man #14 (July 1964) and explain each component briefly while staying concise and respectful.
📨 Input Events:
chat_msg viewer:student_42
"Hi, I need to cite the first Green Goblin appearance for my paper. Can you show me the proper Chicago style?"
Ready for Testing
1
Scene Order
Donation acknowledgment
ID: superchat-thanks
🎯 Goal:
Thank the donor courteously and note, in 1-2 sentences, how their contribution supports archival preservation without encouraging copyright infringement.
📨 Input Events:
superchat viewer:comic_fan88 YouTube $20
"Love your work keeping old comics safe!"
Ready for Testing
2
Scene Order
Detailed catalog record
ID: catalog-entry-long
🎯 Goal:
Produce a 200–250 word catalog entry for Tales of Suspense #39 (March 1963) highlighting Iron Man’s debut, including publication data, creator credits, physical condition notes, and a properly formatted citation at the end.
📨 Input Events:
chat_msg viewer:researcher_7
"Could you draft a full catalog entry for the first Iron Man issue? Aim for a couple hundred words."
Ready for Testing
3
Scene Order
Long-term preservation strategy
ID: preservation-plan
🎯 Goal:
Deliver a methodical 3–4 paragraph plan outlining environmental controls, handling protocols, digitization steps, and reference to at least one professional standard (e.g., ANSI/NISO), written in a clear, organized style.
📨 Input Events:
chat_msg viewer:colleague_mira
"We’re drafting the long-term preservation policy for our Silver Age collection. Can you outline your strategy?"
Ready for Testing
Latency by Model (This Suite)
Fastest
  • [email protected]/Qw… 501 ms
  • p95 • avg • N 6133 ms • 2070 ms • 4
  • [email protected]/Qw… 8482 ms
  • p95 • avg • N 12344 ms • 9242 ms • 4
  • [email protected]/Qw… 9421 ms
  • p95 • avg • N 10235 ms • 9104 ms • 4
  • [email protected]/Qw… 10376 ms
  • p95 • avg • N 16320 ms • 11869 ms • 4
  • meta-llama/llama-3.1-8b… 19087 ms
  • p95 • avg • N 22230 ms • 18687 ms • 5
Slowest
  • microsoft/phi-3-medium-… 454727 ms
  • p95 • avg • N 815745 ms • 471185 ms • 8
  • qwen/qwen3-8b 88332 ms
  • p95 • avg • N 170629 ms • 110418 ms • 8
  • [email protected]/Qw… 46646 ms
  • p95 • avg • N 49295 ms • 45591 ms • 4
  • neversleep/noromaid-20b 38942 ms
  • p95 • avg • N 77923 ms • 39576 ms • 40
  • microsoft/phi-3.5-mini-… 37833 ms
  • p95 • avg • N 192890 ms • 50879 ms • 46
Per-scene duration for this suite.
Suite Actions
Completion Progress 100%
4 of 4 scenes completed
Evaluation Schema
Enhanced Framework
Version v2 ACTIVE
0 dimensions

Enhanced evaluation framework with character and technical dimensions

Top Weighted Dimensions View Details
Character Authenticity
0.182
Plan Validity
0.155
Contextual Intelligence
0.136
Recent Runs
32538891
Dec. 17, 2025, midnight
37619615
Dec. 16, 2025, midnight
30366851
Dec. 15, 2025, midnight
33233465
Dec. 14, 2025, midnight
30088733
Dec. 13, 2025, midnight
36762990
Dec. 12, 2025, midnight
31488842
Dec. 11, 2025, midnight
31009604
Dec. 10, 2025, midnight
34984702
Dec. 9, 2025, midnight
31337177
Dec. 8, 2025, midnight
Latency Overview (This Suite)