# LongMemEval benchmark — Hanzo AI

> LongMemEval benchmark across 4,846 sessions: Hanzo ranks evidence sessions in top 5 for 90.6% of questions vs 85.8% for cosine search.

[Benchmarks](https://hanzo.ai/benchmarks) / LongMemEval

measured

# LongMemEval

Five hundred questions, each with its own haystack of chat sessions around 115k tokens. The engine, frozen on LoCoMo and run here untuned, against the cosine floor on the same vectors across 4,846 sessions.

dataset

[LongMemEval](https://huggingface.co/datasets/xiaowu0162/longmemeval)

licence

MIT

introduced by

[LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://arxiv.org/abs/2410.10813) — Wu et al., 2024

harness

[hanzoai/benchmarks · brain](https://github.com/hanzoai/benchmarks/tree/main/brain/longmemeval)

`node longmemeval/engine.mjs --embed=minilm && node results.mjs`regenerates every table on this page from the raw runs

## What is measured

Five hundred questions, each with its own haystack of chat sessions about 115k tokens long. One or more sessions hold the evidence, and retrieval is scored as recall of those sessions against the benchmark’s own `answer_session_ids`. Every session is embedded turn by turn and ranked by its best turn — 4,846 sessions and 199,641 turns. ALL@5 is the share of questions whose every evidence session is in the top five; ANY@5 is the share with at least one.

Both columns use the same all-minilm vectors. The cosine column ranks a session by its best turn’s cosine. The engine column ranks it by its best turn under the engine’s score, with the configuration frozen on LoCoMo dev at `33d0f8749bd1` — nothing was tuned on this benchmark, so all 500 questions are the report.

## Results

embedder all-minilm · engine `b467901f3950` · run `longmemeval-all-context-minilm`

question type

n

ALL@5 cosine

ALL@5 engine

ANY@5 cosine

ANY@5 engine

ALL@10 cosine

ALL@10 engine

MRR cosine

MRR engine

all questions

500

85.8

90.6

97.4

98.2

93.4

97.0

0.903

0.919

single-session-user

70

95.7

98.6

95.7

98.6

97.1

100.0

0.852

0.872

multi-session

133

75.9

85.7

98.5

99.2

89.5

94.7

0.912

0.917

single-session-preference

30

96.7

96.7

96.7

96.7

96.7

96.7

0.803

0.832

temporal-reasoning

133

75.9

81.2

94.7

95.5

88.7

94.7

0.865

0.894

knowledge-update

78

96.2

98.7

100.0

100.0

98.7

100.0

0.964

0.981

## Where it gains

Every evidence session is in the top five for 90.6% of questions against 85.8% for cosine, and in the top ten for 97.0% against 93.4%. The largest gains are multi-session, where ALL@5 moves from 75.9 to 85.7, and temporal-reasoning, from 75.9 to 81.2. LongMemEval has no fact layer, so the engine’s fact, entity and typed-graph generators propose nothing here; what does the work is lexical match, the session timeline, adjacency and a second hop.

## What this table is not

Session recall is not answer accuracy. Systems reporting LongMemEval scores in the high eighties usually report an end-to-end answer metric with a language-model judge, which is a different measurement and not comparable to these columns. The run uses the release the dataset card now marks deprecated in favour of a cleaned one.

Hanzo AI Cloud

### Build on Hanzo Cloud

[Start on Hanzo Cloud](https://cloud.hanzo.ai)[View Models & Pricing](https://hanzo.ai/pricing)

[PreviousMemoryAgentBench](https://hanzo.ai/benchmarks/memoryagentbench)

[All Benchmarks Board](https://hanzo.ai/benchmarks)

[NextCronQuestions](https://hanzo.ai/benchmarks/cronquestions)

### Related in memory

[LoCoMo](https://hanzo.ai/benchmarks/locomo)[MemoryAgentBench](https://hanzo.ai/benchmarks/memoryagentbench)[LoCoMo · subject scope](https://hanzo.ai/benchmarks/locomo-subject-scope)[LoCoMo-Conv](https://hanzo.ai/benchmarks/locomo-conv)

Other benchmarks[CronQuestions](https://hanzo.ai/benchmarks/cronquestions) · [RepoBench-R](https://hanzo.ai/benchmarks/repobench-r) · [Fleet residency](https://hanzo.ai/benchmarks/fleet) · [Live agent footprint](https://hanzo.ai/benchmarks/goroutine) · [Sandbox cold start](https://hanzo.ai/benchmarks/sandbox) · [Engine prefill on CUDA vs llama.cpp](https://hanzo.ai/benchmarks/inference) · [GPQA-Diamond](https://hanzo.ai/benchmarks/gpqa)

raw runs and scoring: [hanzoai/benchmarks · brain](https://github.com/hanzoai/benchmarks/tree/main/brain/longmemeval) · regenerated by `node longmemeval/engine.mjs --embed=minilm && node results.mjs`