arm
cnn_gemma_l_n200_v1
One config on cnn_dailymail_200, scored one way; its repeats averaged per item.
- dataset
- cnn_dailymail_200
- scored against
- gold/cnn_dailymail_200 gold
- goal
- Short news summaries (CNN)
- runs
- 1
- headline
- coverage 0.320
- last run
- 2026-09-26 07:32
Inspect itAgainst the baselineWith the 35 arms scored the same way
01metrics
| metric | mean | items | better |
|---|---|---|---|
| coverage | 0.320 | 200 | higher |
| compression | 0.108 | 200 | neutral |
| concision | 0.274 | 200 | higher |
| cost_usd | $0.000119 | 200 | lower |
| fmt_bullets | 0.000 | 200 | neutral |
| fmt_label | 0.000 | 200 | neutral |
| fmt_markdown | 0.000 | 200 | neutral |
| fmt_narration | 0.000 | 200 | neutral |
| fmt_overlong | 0.000 | 200 | neutral |
| fmt_paragraphs | 0.000 | 200 | neutral |
| grounding | 0.345 | 200 | higher |
| latency_ms | 2591.1 | 200 | lower |
| length_vs_reference | 1.309 | 200 | neutral |
| reasoning_tokens | 0.000 | 200 | neutral |
| reference_words | 34.7 | 200 | neutral |
| rouge1 | 0.351 | 200 | higher |
| rougeLsum | 0.309 | 200 | higher |
| summary_words | 42.5 | 200 | neutral |
| tokens_in | 755.1 | 200 | lower |
| tokens_out | 55.1 | 200 | lower |
| truncated | 0.000 | 200 | neutral |
02cost and speed
- cost per item
- $0.000119 · 810 tok
- speed per item
- p50 1,817 · p95 6,172 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 |
|---|---|---|---|---|
cnn_gemma_l_n200_v1_20260926T072408Z | 2026-09-26 07:32 | 200 | $0.023709 | measured |
04config
config cnn_gemma_l_n200_v1 · adapter examples/summarization-cnn-dailymail/adapter.py · credentials are never shown
- family
gemma- max_tokens
1200- model
eval-gemma-31b- price_tier
large- prompt_file
prompt.txt- provider
litellm- reasoning
{"enabled": false}- temperature
0.0- usd_per_mtok_in
0.1- usd_per_mtok_out
0.2
05conditions
- data.items_sha256
257feda902391b934b8cde940c15e91201096dbe96ec5a81337e9da007ce3ec7- deployment.model
eval-gemma-31b- deployment.source
adapter- deployment.upstream
openrouter/google/gemma-4-31b-it- fingerprint.version
5- library.numpy
2.4.6- library.openai
3.19.2- library.rouge-score
0.1.2- machine.cpu_count
12- machine.platform
Darwin/x86_64- machine.processor
i386- machine.python
3.11.8- machine.release
24.6.0- reference.sha256
5d0b02c3798017535572d24dd3ce0592332938a0c91e93684d163963a60a7cd9- scorer.id
examples/summarization-cnn-dailymail/adapter.py- scorer.sha256
2fd5227d666d5a1c3110afab4df0df63b3f3bf7f42dab7f5db7c16473efd191f
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 |
|---|---|---|---|
| cnn_gemma_l_n200_v1 · silver | silver/cnn_dailymail_200 silver | coverage | 0.342 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1 | judge judge-summ-pick-v1 | judge_won | 0.001 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-v1 | judge judge-summ-v1 | judge_score | 4.715 |
| cnn_gemma_l_n200_v1 · judged/judge-summ-v2 | judge judge-summ-v2 | judge_score | 4.603 |
07rounds
- Round r1 of Short news summaries (CNN), closed: one of its arms.