run_2026-07-11_nightly
Nightly · v3.2 · 2026-07-11
Claude Sonnet 5.5 · bge-m3 · dense · support-prompt v5 on support-golden-v4 v4.6
Stratified slice of support-golden-v4 (418 items).
Pass rate
78.5%
Faithfulness
0.85
Answer correctness
0.80
Context precision
0.69
Context recall
0.76
Latency p95
3.4s
Failures by category
90 failed samples · largest share: unsupported
| Category | Share |
|---|---|
| Unsupported claims | 24.4% |
| Incorrect factual answers | 18.9% |
| Missing context | 23.3% |
| Retrieval mismatch | 23.3% |
| Instruction-following failures | 6.7% |
| Other | 3.3% |
Run details
- Dataset
- support-golden-v4 v4.6 · 418 items
- Generator
- Claude Sonnet 5.5
- Retriever
- bge-m3 · dense
- Prompt
- support-prompt v5
- Judge
- LLM judge · Claude Opus 5.5 · rubric v3
- Started
- Jul 11, 02:00 UTC
- Duration
- 45m 7s
- Triggered by
- Scheduler
- Tokens / request
- 3,870 in · 230 out
- nightly
- golden-slice
All metrics
Retrieval, generation and operational metrics
| Metric | Group | This run |
|---|---|---|
| Pass rateShare of samples the judge marked as passing all rubric checks. | Outcome | 78.5% |
| FaithfulnessShare of answer claims supported by the retrieved context. | Generation | 0.85 |
| Answer correctnessAgreement with the gold answer on facts, not style. | Generation | 0.80 |
| Instruction adherenceRespect for tone, format, length, language and policy constraints. | Generation | 0.86 |
| Context precisionRank-weighted precision of relevant chunks passed to the generator. | Retrieval | 0.69 |
| Context recallShare of gold-answer statements supported by the retrieved context. | Retrieval | 0.76 |
| Recall@5Share of gold passages found in the top 5 retrieved chunks. | Retrieval | 0.78 |
| MRRMean reciprocal rank of the first relevant chunk. | Retrieval | 0.64 |
| NDCG@10Graded ranking quality of the top 10, normalized by the ideal order. | Retrieval | 0.73 |
| Latency p50Median end-to-end time to final token. | Operational | 1.8s |
| Latency p9595th percentile end-to-end time to final token. | Operational | 3.4s |
| Cost per requestModel, embedding and reranking cost per answered request (USD). | Operational | $0.0044 |
Nightly trend
Nightly runs on the support-golden-v4 slice, Jul 11 to Oct 8. This run is one point in the series.
Across datasets
support-assistant v3.2 on every dataset in the project. Rows marked “matrix” come from the comparison matrix rather than a dedicated run.
| Dataset | Items | Pass rate | Faith. | Ctx recall | Recall@5 | p95 | Source |
|---|---|---|---|---|---|---|---|
| support-golden-v4this run | 1,240 | 78.5% | 0.85 | 0.76 | 0.78 | 3.4s | This run |
| billing-edge-cases | 312 | Not evaluated with this configuration | |||||
| roaming-and-travel | 188 | Not evaluated with this configuration | |||||
| device-troubleshooting | 426 | Not evaluated with this configuration | |||||
| account-security | 154 | Not evaluated with this configuration | |||||
| locale-formatting | 96 | Not evaluated with this configuration | |||||
| synthetic-hard-negatives | 540 | Not evaluated with this configuration | |||||
Traced samples
17 samples with full traces (4 failing, 13 passing), stratified by domain. Open a row to inspect retrieval and the judge's reasoning.
Is there a restocking fee if I return an opened phone? Returns & warranty FailMissingjudge 0.13 |
My son is 15. Can he have his own line on my account? Plans & upgrades FailIncorrectjudge 0.10 |
How much data can I use in Germany on Unlimited Plus before I get charged? Roaming & travel FailMismatchjudge 0.18 |
Does the Fall 2026 upgrade offer work with a family plan discount? Promotions Passjudge 0.89 |
What is the late fee if I pay my bill after the due date? Billing & payments Passjudge 0.87 |
How long does it take to port my number to Harbor? Number porting Passjudge 0.94 |
How do I get a copy of the personal data Harbor holds about me? Data privacy requests Passjudge 0.94 |
My phone shows 4G but mobile data does not work after the iOS update. Device troubleshooting Passjudge 0.97 |
Is SIM swap protection turned on by default? Account & security Passjudge 0.87 |
What is the excess on a theft insurance claim? Returns & warranty Passjudge 0.86 |