arm
sf_llama_s_n200_v1
One config on scifact_200, scored one way; its repeats averaged per item.
- dataset
- scifact_200
- scored against
- gold/scifact_200 gold
- goal
- Evidence retrieval for scientific claims (SciFact)
- runs
- 1
- headline
- ndcg_10 0.717
- last run
- 2026-09-28 19:23
Inspect itAgainst the baselineWith the 26 arms scored the same way
01metrics
| metric | mean | items | better |
|---|---|---|---|
| ndcg_10 | 0.717 | 200 | higher |
| cost_usd | $0.000729 | 200 | lower |
| duplicate_ids | 0.000 | 200 | neutral |
| found_any | 0.865 | 200 | neutral |
| latency_ms | 17481.6 | 200 | lower |
| llm_named_unknown | 0.200 | 200 | neutral |
| llm_parsed | 0.980 | 200 | neutral |
| mrr_10 | 0.707 | 200 | higher |
| n_relevant | 1.135 | 200 | neutral |
| n_returned | 100.0 | 200 | neutral |
| parsed | 1.000 | 200 | higher |
| rank_of_first | 2.825 | 200 | neutral |
| reasoning_tokens | 0.000 | 200 | neutral |
| recall_10 | 0.785 | 200 | higher |
| recall_100 | 0.859 | 200 | higher |
| tokens_in | 3848.3 | 200 | lower |
| tokens_out | 164.8 | 200 | lower |
| truncated | 0.000 | 200 | neutral |
| unknown_ids | 0.000 | 200 | neutral |
02cost and speed
- cost per item
- $0.000729 · 4,013 tok
- speed per item
- p50 13,661 · p95 42,002 ms
Per item, over its items: cost as dollars and tokens (a local model is free but still uses tokens), speed as the median and the slow tail (p95). A goal that names this arm weighs them in its decision.
03runs
| run | made | items | cost | how |
|---|---|---|---|---|
sf_llama_s_n200_v1_20260928T192318Z | 2026-09-28 19:23 | 200 | $0.145845 | reparse |
04config
config sf_llama_s_n200_v1 · adapter examples/retrieval-scifact/adapter.py · credentials are never shown
- corpus_id
scifact- family
llama- max_tokens
700- model
eval-llama-scout- price_tier
small- prompt_file
prompt.txt- provider
rerank- reasoning
{"enabled": false}- rerank_k
20- snippet_chars
900- temperature
0.0- top_k
100- usd_per_mtok_in
0.08- usd_per_mtok_out
0.3
05conditions
- data.items_sha256
b97dfe735a78eb4978cde41e2ca9a0bff424de9e6a0a2bdada5d167e3423004d- deployment.model
eval-llama-scout- deployment.source
adapter- fingerprint.version
5- library.numpy
1.26.4- library.openai
3.19.2- library.scikit-learn
1.9.1- library.sentence-transformers
3.4.1- library.torch
2.2.2- library.transformers
4.55.4- machine.cpu_count
12- machine.label
mac-dev- machine.platform
Darwin/x86_64- machine.processor
i386- machine.python
3.11.8- machine.release
24.6.0- reference.sha256
b522e08017ebc7dd71c5627bccfdd688c5124096df8a5e6454684141bc361d99- scorer.id
examples/retrieval-scifact/adapter.py- scorer.sha256
46cd2bd89061c9f3bff0493cce7ab292dd6f9b1bae7c7e482af0aebdd1479cee
06the same config, scored other ways
scored against silverscored by a judgescored against a label set, not a reference setunmarked rows are scored against gold
| arm | scored against | headline | mean |
|---|---|---|---|
| sf_llama_s_n200_v1 · repeats | gold/scifact_200 gold | ndcg_10 | 0.713 |
07rounds
- Round r1 of Evidence retrieval for scientific claims (SciFact), closed: one of its arms.