run_2026-10-06_gemini-2-5-pro
v3.4 · Gemini 2.5 Pro comparison
Gemini 2.5 Pro · bge-m3 · hybrid (BM25 + dense, RRF) · support-prompt v7 on support-golden-v4 v4.6
Pass rate
83.8%
Faithfulness
0.88
Answer correctness
0.86
Context precision
0.79
Context recall
0.84
Latency p95
4.6s
Failures by category
201 failed samples · largest share: unsupported
| Category | Share | vs reference |
|---|---|---|
| Unsupported claims | 25.4% | −1.8 pts |
| Incorrect factual answers | 22.9% | +1.9 pts |
| Missing context | 18.9% | −0.2 pts |
| Retrieval mismatch | 17.9% | 0.0 pts |
| Instruction-following failures | 10.9% | −0.2 pts |
| Other | 4.0% | +0.3 pts |
Run details
- Dataset
- support-golden-v4 v4.6 · 1,240 items
- Generator
- Gemini 2.5 Pro
- Retriever
- bge-m3 · hybrid (BM25 + dense, RRF)
- Prompt
- support-prompt v7
- Judge
- LLM judge · Claude Opus 5.5 · rubric v3
- Started
- Oct 6, 14:06 UTC
- Duration
- 2h 54m
- Triggered by
- Maya Collins
- Tokens / request
- 3,420 in · 236 out
- Compared with
- support-assistant v3.4 · release candidate
- comparison
All metrics
Against support-assistant v3.4 · release candidate
| Metric | Group | This run | Reference | Change |
|---|---|---|---|---|
| Pass rateShare of samples the judge marked as passing all rubric checks. | Outcome | 83.8% | 86.9% | −3.1 pts |
| FaithfulnessShare of answer claims supported by the retrieved context. | Generation | 0.88 | 0.91 | −0.03 |
| Answer correctnessAgreement with the gold answer on facts, not style. | Generation | 0.86 | 0.88 | −0.02 |
| Instruction adherenceRespect for tone, format, length, language and policy constraints. | Generation | 0.91 | 0.93 | −0.02 |
| Context precisionRank-weighted precision of relevant chunks passed to the generator. | Retrieval | 0.79 | 0.79 | 0.00 |
| Context recallShare of gold-answer statements supported by the retrieved context. | Retrieval | 0.84 | 0.84 | 0.00 |
| Recall@5Share of gold passages found in the top 5 retrieved chunks. | Retrieval | 0.88 | 0.88 | 0.00 |
| MRRMean reciprocal rank of the first relevant chunk. | Retrieval | 0.74 | 0.74 | 0.00 |
| NDCG@10Graded ranking quality of the top 10, normalized by the ideal order. | Retrieval | 0.81 | 0.81 | 0.00 |
| Latency p50Median end-to-end time to final token. | Operational | 2.3s | 1.9s | +0.4s |
| Latency p9595th percentile end-to-end time to final token. | Operational | 4.6s | 3.8s | +0.8s |
| Cost per requestModel, embedding and reranking cost per answered request (USD). | Operational | $0.0048 | $0.0042 | +0.0006 |
Nightly trend
Nightly runs on the support-golden-v4 slice, Jul 11 to Oct 8. Dashed line marks this run.
- Pass rate · nightly
- This run · 83.8%
Across datasets
v3.4 · Gemini 2.5 Pro 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 | 83.8% | 0.88 | 0.84 | 0.88 | 4.6s | This run |
| billing-edge-cases | 312 | 78.8% | 0.84 | 0.82 | 0.86 | 4.8s | matrix |
| roaming-and-travel | 188 | 78.2% | 0.85 | 0.79 | 0.83 | 4.7s | matrix |
| device-troubleshooting | 426 | 81.5% | 0.86 | 0.83 | 0.87 | 5.3s | matrix |
| account-security | 154 | 85.1% | 0.89 | 0.85 | 0.89 | 4.5s | matrix |
| locale-formatting | 96 | 78.1% | 0.84 | 0.80 | 0.84 | 4.9s | matrix |
| synthetic-hard-negatives | 540 | 73.3% | 0.83 | 0.73 | 0.77 | 4.8s | matrix |
Traced samples
18 samples with full traces (5 failing, 13 passing), stratified by domain. Open a row to inspect retrieval and the judge's reasoning.
My eSIM stopped working after I reset my phone. Do I need to pay for a new one? eSIM & activation FailUnsupportedjudge 0.12 |
Why was I charged twice for my September bill? Billing & payments Passjudge 0.97 |
If I upgrade my plan mid-month, how is my next bill calculated? Plans & upgrades Passjudge 0.89 |
How much data can I use in the EU on the Unlimited Plus plan? Roaming & travel Passjudge 0.95 |
My eSIM QR code says it has already been used. What should I do? eSIM & activation Passjudge 0.94 |
What is the late fee if I pay my bill after the due date? Billing & payments Passjudge 0.90 |
What is the excess on a theft insurance claim? Returns & warranty Passjudge 0.94 |
Is SIM swap protection turned on by default? Account & security Passjudge 0.90 |
My phone shows 4G but mobile data does not work after the iOS update. Device troubleshooting Passjudge 0.96 |
Can I return a phone I bought online if I opened the box? Returns & warranty Passjudge 0.94 |