BENCHMARK · MESA 0.9.3

MESA 0.9.3 benchmark report

Same retrieval quality, faster ingest: with the built-in reranker, 0.9.2 and 0.9.3 both reach Hit@5 74.4% and MRR 0.656 at the displayed precision.

74.4%

Hit@5

Correct passage in the first five results

57.9%

Hit@1

Correct passage in the first result

0.656

MRR

Ranking of the first correct passage

100.0%

Citation Hit@5

Explicit citation questions

MESA 0.9.3 · BGE-M3 + built-in BGE reranker (T2)

Search results

November 18, 2026 · 141 documents · 121 / 145 answerable test questions

Built-in configurations
ConfigurationHit@5Hit@1MRRHit@10Doc@1Doc@5p50p95Hardware
Models off (T0)20261117T230132Z_v09338.0%22.3%0.29747.9%43.8%57.9%0.45 s0.94 sColab A100-SXM4-80GB
BGE-M3 embeddings (T1b)20261117T230132Z_v09367.8%38.8%0.52277.7%57.9%77.7%1.37 s2.36 sColab A100-SXM4-80GB

Results by question type

Hit@5 per question type. Darker cells mean the right passage was found more often.

Correct passage in the first five results
Question typeModels off (T0)BGE-M3 embeddings (T1b)BGE-M3 + built-in BGE reranker (T2)
Exact wording (36) 69.4%88.9%97.2%
Paraphrase (39) 18.0%69.2%71.8%
Cross-document (17) 35.3%52.9%76.5%
Number, date or docket (29) 27.6%48.3%48.3%

Citation questions

0.9.3 keeps the 0.9.2 result: explicit citation Hit@5 is 100.0% (50/50) for T0, T1b and T2. Natural wording is 97.5% (39/40) for T0 and T1b, and 100.0% (40/40) for T2.

Citation questions, Hit@5
ConfigurationExplicit citation (50)Natural wording (40)
Models off (T0)100.0%97.5%
BGE-M3 embeddings (T1b)100.0%97.5%
BGE-M3 + built-in BGE reranker (T2)100.0%100.0%

Time until searchable

Full corpus ingestion
ConfigurationTotal timeChunksSeconds per chunkHardware
Models off (T0)7.4 min5,0410.09 sColab A100-SXM4-80GB
BGE-M3 embeddings (T1b)12.0 min5,0410.14 sColab A100-SXM4-80GB

0.9.3 batches ingest work; retrieval quality is unchanged.

Download results

Report and aggregate metrics (JSON) ↓

How we measured

Tier M contains 141 Turkish laws, regulations and court decisions. A language model generated questions from the corpus. A separate model and rule checks reviewed them. Configurations were chosen on 101 development questions before evaluation on 145 held-out questions. Retrieval scores use the 121 answerable questions.

What do the metrics mean?
Hit@1 · Hit@5 · Hit@10
Share of questions with the correct passage in the first 1, 5 or 10 results.
MRR
Average reciprocal rank of the first correct passage. A score of 1 means it always came first.
Doc@1 · Doc@5
Share of questions with the correct document among the first 1 or 5 results.
p50 · p95
Half of queries finished within p50 and 95% within p95. Both are measured in seconds.

Scope and limitations

The test measures whether MESA retrieves the correct passage or document. The 24 questions with no answer in the corpus are outside the retrieval scores. The corpus is small and its decisions come from the Court of Cassation. The questions are synthetic.

For number, date and docket questions, the T2 result is unchanged in 0.9.3: 14/29 = 48.3% Hit@5. The benchmark requests 50 results. With a 10-result request the reranker sees 20 candidates; on the dev split Hit@5 was 75.3% instead of 77.7%. This comparison changes both the candidate pool and the number of returned results.

0.9.3 run: 18 November 2026 · mesa-memory 0.9.3 · 20261117T230132Z_v093.