LoCoMo v1, all 1,986 questions, Top 30Season 1 · Rank 2 of 7

Recalld, retrieval search

Recalld (hosted API, v1)recalld/cloud

Report a problem with this result (see the corrections policy)

The judge ruled the retrieved context correct for 1,703 of 1,986 questions (85.8%, 95% CI 84.6 to 87.2), using 1,199 tokens per question on average.

Figures

Context

Tokens per question, mean
1,199
Tokens, 95th percentile
1,403
Accuracy per 1,000 tokens
71.5
Contexts cut to the budget
0.0%

Speed

Retrieval, median
287 ms
Retrieval, 95th percentile
2.35 s
Ingestion, total
9 h 40 min (all conversations added up)
Ingestion, per turn
5.92 s

Judge cost

Top 10
$9.99
Top 30
$14.45
Whole run
$24.44from price table 2026-10-04

Checks

Abstention accuracy
92.4%
No verdict (call failed)
0
Flagged by the judge
19

Where it fails

Accuracy by question category, with 95% confidence intervals. A low category is where the memory system misses the context the question needs.

Accuracy by category
CategoryCorrectAccuracy95% CITokensNo verdict
adversarial412 of 44692.4%90.7 to 94.01,1750
multi-hop182 of 28264.5%59.0 to 69.81,1670
open-domain54 of 9656.3%39.6 to 74.71,1430
single-hop775 of 84192.2%89.7 to 94.51,2030
temporal280 of 32187.2%83.9 to 90.41,2660

Every question

One square per question, grouped by category. Select a square to read the question, the gold answer, the judge's reason and the context it was given.

Loading questions…

Retrieval latency

The share of questions whose context came back within a given time. Further left is faster.

Other runs of this connector

Earlier and later runs on this board stay listed. A different code hash means the connector code changed between runs.

FinishedRunCode hashAccuracy
1 Nov 2026Recalld, retrieval recall2c22ea08620287.8%

Judge

A season is one fixed set of judging rules: one pinned judge model, its settings and its prompt rule on every question. When the rules change a new season starts, and earlier runs are judged again from their stored contexts, without re-running the memory system. Seasons

Model
claude-sonnet-5-5
Route
anthropic
Season
Season 1
Effort
medium
Output limit
4,000 tokens
Prompt
v3 sha256:ce6d9750331c79d1bb3a0737109c458fef4ba9fd8cf929c75c1c1cf9407a4b78
Served by
claude-sonnet-5-5

How this result was produced

Everything below is part of the signed result. Change any of it and the signature no longer matches.

Run

Run id
20261101T190122Z-157588
Mode
hosted runner
Finished
1 Nov 2026
Duration
3 h 13 min
memjudge version
0.1.0
Commit
a73cf373d958
Image
sha256:8119890e8697d791a388f2397208dbc8cb236a01319e1d74e36fd616660fce2c
Context budget
8,192 tokens (o200k_base)
Conversations at a time
4
Submitter affiliated
yes, with Recalld

Dataset

Name
locomo v1
Questions
1,986
Licence
CC-BY-NC-4.0
Corrections applied
0
Hash
sha256:9c7812f2f45ce12b06cd9d3fc55736c3a8a83d2b263c11f28c292c475f6ddf38
Source file hash
79fa87e90f04081343b8c8debecb80a9a6842b76a7aa537dc9fdf651ea698ff4

Connector

Connector
recalld/cloud
Written by
the vendor
SDK
none (plain HTTP)
Endpoint
https://us.recalld.ai
Code hash
sha256:2c22ea086202c1a0314c13ce277063b23d34661d5224589f4409344c6a2094c4
Models
openai-gpt-6-luna, gemini-embedding-002-vertex
retrieval
search
decompose model
openai-gpt-6-luna
evaluate model
openai-gpt-6-luna
select model
openai-gpt-6-luna
embedding model
gemini-embedding-002-vertex
base url
default
max retries
4
timeout s
300
batch
off
allow non eu
off
batch poll s
60

Raw files

FileSHA-256
conversations.jsonl1f72a97a1b27c550770222751705b0acf9d1ad17a86945ad3809ff7cb59322eb
questions-top10.jsonl5b9703f445b4bec92a443bd6357a46377821104218c41969b657bdcabe40d91a
questions-top30.jsonld64dd97190865648c1de54af3d5846de5405974e2160d9652017cccf9190cb90

Check it yourself

The signed result is signed with key 478df5eb628bfa74, one of the trusted keys published in the leaderboard repository. Download it and verify it with the memjudge command-line tool; add --artifactswith the raw files to check those too. How signing works.

memjudge verify 20261101T190122Z-157588.json

Download the signed result

Questions, answers and conversation excerpts on this page come from LoCoMo (Maharana et al., 2024, Snap Research) and are used under CC BY-NC 4.0 (non-commercial use only). They are reformatted, and corrected where MemJudge's errata apply. MemJudge's own verdicts and scores are CC BY 4.0.