LoCoMo v1, all 1,986 questions, Top 30Season 1 · Rank 4 of 7
Supermemory
Supermemory (hosted API, v5)supermemory/cloud
Report a problem with this result (see the corrections policy)
The judge ruled the retrieved context correct for 1,607 of 1,986 questions (80.9%, 95% CI 78.7 to 83.3), using 2,334 tokens per question on average.
Figures
Context
- Tokens per question, mean
- 2,334
- Tokens, 95th percentile
- 3,255
- Accuracy per 1,000 tokens
- 34.7
- Contexts cut to the budget
- 0.0%
Speed
- Retrieval, median
- 319 ms
- Retrieval, 95th percentile
- 775 ms
- Ingestion, total
- 3 h 10 min (all conversations added up)
- Ingestion, per turn
- 1.94 s
Judge cost
- Top 10
- $12.46
- Top 30
- $22.41
- Whole run
- $34.87from price table 2026-10-04
Checks
- Abstention accuracy
- 93.9%
- No verdict (call failed)
- 0
- Flagged by the judge
- 26
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.
| Category | Correct | Accuracy | 95% CI | Tokens | No verdict |
|---|---|---|---|---|---|
| adversarial | 419 of 446 | 93.9% | 92.2 to 96.1 | 2,298 | 0 |
| multi-hop | 202 of 282 | 71.6% | 65.8 to 78.4 | 2,315 | 0 |
| open-domain | 53 of 96 | 55.2% | 36.1 to 72.0 | 2,406 | 0 |
| single-hop | 782 of 841 | 93.0% | 91.5 to 94.7 | 2,390 | 0 |
| temporal | 151 of 321 | 47.0% | 36.1 to 58.2 | 2,232 | 0 |
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.
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
- 20261101T114259Z-05d6c0
- Mode
- hosted runner
- Finished
- 1 Nov 2026
- Duration
- 1 h 23 min
- memjudge version
- 0.1.0
- Commit
- 896c4f7b13f7
- Image
- sha256:8671c6e11fb4468e182e776556e616e221df73a4f77051716772e8cd4238222e
- Context budget
- 8,192 tokens (o200k_base)
- Conversations at a time
- 4
- Submitter affiliated
- no
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
- supermemory/cloud
- Written by
- MemJudge maintainers
- SDK
- supermemory==5.0.0
- Endpoint
- https://api.supermemory.ai
- Code hash
- sha256:c9e53310a709c5efaf804ced8772eb54d8e4c994f20ebc3901c16ec48a901d43
- Models
- chosen by the vendor, not disclosed
- dreaming
- instant
- poll interval s
- 1
- ingest timeout s
- 3600
- base url
- default
Raw files
| File | SHA-256 |
|---|---|
| conversations.jsonl | cd9bfd31da9a64a0d6c8291639d37b5e3bddb5097eddede6b0e11df29868d3b2 |
| questions-top10.jsonl | e2b8044e66f3c894adc8444e7adc0bd1723949690997f03aca0c4c5de0dcde9b |
| questions-top30.jsonl | 3fd804e76facb4e4db3b398ef2ae90082376d6a839b91e88e7c1fcfeef52b484 |
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 20261101T114259Z-05d6c0.jsonQuestions, 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.