model
eval-claude-haiku llm
A model record: onboarded once for the project and used by any eval's arms.
- weights
- proprietary
- aliases
eval-claude-haiku- settings
- defaults
- onboarding
- not onboarded:
evh model-onboard - best result per goal
- #11 of 33 A scorer that agrees with experts on summaries (SummEval)
#10 of 28 Encyclopedia topic classification (DBpedia)
#14 of 29 Short news summaries (CNN)
#18 of 28 Named-entity extraction (Few-NERD)
#24 of 30 News topic classification (AG News)
01deployments and their onboarding
No deployment is recorded for this model. Not onboarded yet: evh model-onboard eval-claude-haiku.
02settings history
No change of settings or build is recorded.
03arms
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| ag_anthropic_s_n200_v1 · adjudicated ag_news_200 | — | — | max_tokens 200, temperature 0.0 | none | correct 0.925 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1 cnn_dailymail_200 | — | — | max_tokens 1200, temperature 0.0 | none | judge_won 0.226 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-v1 cnn_dailymail_200 | — | — | max_tokens 1200, temperature 0.0 | none | judge_score 4.952 |
| cnn_anthropic_s_n200_v1 · judged/judge-summ-v2 cnn_dailymail_200 | — | — | max_tokens 1200, temperature 0.0 | none | judge_score 4.728 |
| cnn_anthropic_s_n200_v1 · silver cnn_dailymail_200 | — | — | max_tokens 1200, temperature 0.0 | none | coverage 0.469 |
| ag_anthropic_s_n200_v1 ag_news_200 | — | News topic classification (AG News) | max_tokens 200, temperature 0.0 | none | correct 0.840 |
| cnn_anthropic_s_n200_v1 cnn_dailymail_200 | — | Short news summaries (CNN) | max_tokens 1200, temperature 0.0 | none | coverage 0.324 |
| db_anthropic_s_n200_v1 dbpedia_280 | — | Encyclopedia topic classification (DBpedia) | max_tokens 200, temperature 0.0 | none | correct 0.979 |
| fn_anthropic_s_n200_v1 few_nerd_280 | — | Named-entity extraction (Few-NERD) | max_tokens 600, temperature 0.0 | none | f1 0.584 |
| se_anthropic_s_n100_v1 summeval_100 | — | A scorer that agrees with experts on summaries (SummEval) | max_tokens 1500, temperature 0.0 | none | tau 0.484 |