Skip to content

run_2026-07-25_nightly

Nightly · v3.2 · 2026-07-25

Claude Sonnet 5.5 · bge-m3 · dense · support-prompt v5 on support-golden-v4 v4.6

CompletedNightlysupport-assistant v3.2v2 · 512 tokens / 64 overlap
Compare

Stratified slice of support-golden-v4 (423 items).

Pass rate

78.3%

+0.2 pts(improvement)vs previous nightly331 of 423 samples passed

Faithfulness

0.85

0.00(no change)vs previous nightly

Answer correctness

0.81

0.00(no change)vs previous nightly

Context precision

0.69

−0.02(regression)vs previous nightly

Context recall

0.75

+0.01(improvement)vs previous nightly

Latency p95

3.5s

−0.1s(improvement)vs previous nightly

Failures by category

92 failed samples · largest share: unsupported

Share of failed samples by category, compared with Nightly · v3.2 · 2026-07-24
CategorySharevs reference
Unsupported claims23.9%−0.5 pts
Incorrect factual answers19.6%+0.7 pts
Missing context22.8%−0.5 pts
Retrieval mismatch23.9%+0.6 pts
Instruction-following failures6.5%−0.1 pts
Other3.3%−0.1 pts

Run details

Dataset
support-golden-v4 v4.6 · 423 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 25, 02:00 UTC
Duration
41m 28s
Triggered by
Scheduler
Tokens / request
3,870 in · 230 out
  • nightly
  • golden-slice

All metrics

Against Nightly · v3.2 · 2026-07-24

All metrics for Nightly · v3.2 · 2026-07-25
MetricThis runReferenceChange
Pass rate78.3%78.1%+0.2 pts
Faithfulness0.850.850.00
Answer correctness0.810.810.00
Instruction adherence0.880.87+0.01
Context precision0.690.71−0.02
Context recall0.750.74+0.01
Recall@50.770.770.00
MRR0.650.63+0.02
NDCG@100.720.720.00
Latency p501.8s1.7s0.0s
Latency p953.5s3.5s−0.1s
Cost per request$0.0044$0.00440.0000

Nightly trend

Nightly runs on the support-golden-v4 slice, Jul 11 to Oct 8. This run is one point in the series.

Pass rate moved from 78.5% to 87.2% across 90 nightly runs. Configuration changes: v3.3 on Aug 4, v3.4 on Sep 8.

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.

Configuration results per dataset
DatasetItemsPass rateFaith.Ctx recallRecall@5p95Source
support-golden-v4this run1,240
78.3%
0.850.750.773.5sThis run
billing-edge-cases312Not evaluated with this configuration
roaming-and-travel188Not evaluated with this configuration
device-troubleshooting426Not evaluated with this configuration
account-security154Not evaluated with this configuration
locale-formatting96Not evaluated with this configuration
synthetic-hard-negatives540Not 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.

Traced samples for Nightly · v3.2 · 2026-07-25

Why was I charged twice for my September bill?

Billing & payments

Passjudge 0.87

If I upgrade my plan mid-month, how is my next bill calculated?

Plans & upgrades

Passjudge 0.96

How much data can I use in the EU on the Unlimited Plus plan?

Roaming & travel

Passjudge 0.92

My eSIM QR code says it has already been used. What should I do?

eSIM & activation

Passjudge 0.95

What is the late fee if I pay my bill after the due date?

Billing & payments

Passjudge 0.89

Is SIM swap protection turned on by default?

Account & security

Passjudge 0.95

My phone shows 4G but mobile data does not work after the iOS update.

Device troubleshooting

Passjudge 0.91

Can I return a phone I bought online if I opened the box?

Returns & warranty

Passjudge 0.95

How do I get a copy of the personal data Harbor holds about me?

Data privacy requests

Passjudge 0.93

My bill says 41,20 €. Is that forty-one euros or four thousand?

Billing & payments

Passjudge 0.96