LangMem vs Mem0: accuracy, cost and latency
Independent results on the same 30 questions of LongMemEval-S (cleaned, 2025-09), with the same reader model and the official judge. Pilot sample, so accuracy is shown with 95% intervals.
Verdict
Generated from the pilot data, n=30 per system- AccuracyMem0 is more accurate: 83.3% (95% CI 66–93%) vs 33.3% (95% CI 19–51%) for LangMem. The 95% intervals do not overlap, even at n=30.
- CostLangMem costs 1.5× less per 1,000 questions: $61.6 vs $93.0 for Mem0.
- LatencyLangMem answers faster: median 3.5s vs 4.3s for Mem0 per question (p90 5.3s vs 7.4s).
- IngestionLangMem ingests a chat history faster: 8.5 min vs 15.2 min for Mem0 (median per question).
- ContextThe reader sees a median of 23k characters of context per question with LangMem and 50k with Mem0.
Key numbers side by side
Bold marks the better value. Accuracy rows are not bolded when the 95% intervals overlap.
| Metric | LangMem | Mem0 |
|---|---|---|
| Accuracy (official judge) | 33.3% | 83.3% |
| 95% interval | 19–51% | 66–93% |
| Panel accuracy | 26.7% | 83.3% |
| Cost per 1,000 questions | $61.6 | $93.0 |
| of which memory side | $61.0 | $91.6 |
| of which answering | $0.61 | $1.32 |
| Latency p50 | 3.5s | 4.3s |
| Latency p90 | 5.3s | 7.4s |
| Ingestion per history (median) | 8.5 min | 15.2 min |
| Context given to reader (median chars) | 23k | 50k |
LangMem and Mem0 among all tested systems
LangMem and Mem0 are highlighted; other systems are muted for context, baselines lightest. Each name links to the system's page.
Accuracy
Higher is betterShare of 30 questions answered correctly (official judge). Whiskers: 95% interval.
- Cognee90.0%74–97%
- Hindsight90.0%74–97%
- Plain RAG86.7%70–95%
- Mem083.3%66–93%
- Full context83.3%66–93%
- LangMem33.3%19–51%
Not shown: Graphiti (pilot result withdrawn, rerun in progress).
Cost per 1,000 questions
Lower is betterUSD billed (prices as of 2026-10-08). Solid: memory side (ingestion and retrieval). Light: answering.
Not shown: Graphiti (pilot result withdrawn, rerun in progress).
Latency per question
Lower is betterRetrieval plus answer, in seconds. Solid: median (p50). Light: up to p90.
- LangMem3.5sp90 5.3s
- Cognee4.0sp90 8.1s
- Mem04.3sp90 7.4s
- Full context4.8sp90 8.0s
- Plain RAG4.8sp90 7.4s
- Hindsight5.4sp90 8.1s
Not shown: Graphiti (pilot result withdrawn, rerun in progress).
Ingestion time
Lower is betterMedian time to load one question's chat history into the system.
Not shown: Graphiti (pilot result withdrawn, rerun in progress).
Accuracy by question type
Difference is LangMem minus Mem0, in percentage points. Each type has only a few pilot questions (n), so one question can move a row by 13 points or more.
| Question type | n | LangMem | Mem0 | Difference |
|---|---|---|---|---|
| Single-session (user) | 4 | 75% | 75% | 0 |
| Single-session (assistant) | 3 | 0% | 100% | −100 pts in favour of Mem0 |
| Preferences | 2 | 50% | 100% | −50 pts in favour of Mem0 |
| Multi-session | 8 | 13% | 75% | −62 pts in favour of Mem0 |
| Knowledge update | 4 | 50% | 100% | −50 pts in favour of Mem0 |
| Temporal reasoning | 8 | 38% | 88% | −50 pts in favour of Mem0 |
| Abstention | 1 | 0% | 0% | 0 |
What each one is
LangMem
A memory manager that asks an LLM to extract, consolidate and update memories in a LangGraph store.
How we ran it
create_memory_store_manager with default instructions, one invoke() per session, LangGraph InMemoryStore with OpenAI embeddings, store.search() with the default limit (10).
Mem0
Extracts short memories from each exchange with an LLM, stores them in a vector store, and retrieves them with semantic, keyword and entity signals.
How we ran it
Open-source SDK with local Qdrant, NLP extras installed (spaCy, BM25). Mirrors Mem0's own LongMemEval harness: one add() per user+assistant pair, top_k=200 at search. Historical timestamps are platform-only, so the shared clock simulation supplies dates.
What the vendors report
LangMem
| Score | Variant | Reader | Judge | Note | Source |
|---|---|---|---|---|---|
| 33.3% | S (cleaned, 2025-09), 30-question pilot | openai/gpt-6-luna | gpt-4o-2024-08-06, official prompt | MemVerdict measurement, LangMem 0.0.30 | This page |
| None found | - | - | - | No self-reported LongMemEval score found. | - |
Mem0
| Score | Variant | Reader | Judge | Note | Source |
|---|---|---|---|---|---|
| 83.3% | S (cleaned, 2025-09), 30-question pilot | openai/gpt-6-luna | gpt-4o-2024-08-06, official prompt | MemVerdict measurement, Mem0 2.2.1 (open source) | This page |
| 94.4% | S | GPT-5 | GPT-5 with Mem0's own lenient prompt | Managed platform, not the open-source SDK. | mem0.ai/research |
Vendor-reported scores and ours are measured differently, so a gap does not by itself mean either number is wrong. Our pilot uses openai/gpt-6-luna as the reader that writes each answer, gpt-4o-2024-08-06 with the official LongMemEval judge prompt, LongMemEval-S (cleaned, 2025-09) and 30 questions, with each system set up as described above. Scores move with the reader model, the judge model and its prompt, the dataset version, the number of questions, and whether a hosted platform or the open-source package is tested.
Frequently asked questions
Is LangMem better than Mem0?
Mem0 is more accurate: 83.3% (95% CI 66–93%) vs 33.3% (95% CI 19–51%) for LangMem. The 95% intervals do not overlap, even at n=30. With the 3-judge panel majority instead of the official judge: LangMem 26.7%, Mem0 83.3%. The largest gap by question type is Multi-session: 1 of 8 vs 6 of 8 correct, in Mem0's favour; each question type has only 1 to 8 questions in this pilot. These are pilot numbers (30 questions each); the full 500-question run will narrow the intervals.
Which is cheaper, LangMem or Mem0?
LangMem costs 1.5× less per 1,000 questions: $61.6 vs $93.0 for Mem0. LangMem: $61.6 per 1,000 questions, of which $61.0 (99%) is memory-side (ingestion and retrieval) and $0.61 is answering. Mem0: $93.0 per 1,000 questions, of which $91.6 (99%) is memory-side (ingestion and retrieval) and $1.32 is answering. Prices as of 2026-10-08.
Which is faster, LangMem or Mem0?
LangMem answers faster: median 3.5s vs 4.3s for Mem0 per question (p90 5.3s vs 7.4s). LangMem ingests a chat history faster: 8.5 min vs 15.2 min for Mem0 (median per question). Latency is measured per question as retrieval plus answering; ingestion is the time to load one question's chat history.
How were LangMem and Mem0 tested?
Both were run on the same 30 questions of LongMemEval-S (cleaned, 2025-09) as every other system, by the same harness. For each question, the system ingests that question's chat history, then retrieves context that one reader model (openai/gpt-6-luna) uses to answer with the official LongMemEval prompt. Answers are graded by the official judge (gpt-4o-2024-08-06) and cross-checked by 3 other judges; all judges agreed on 95% of graded answers. Costs are what the providers billed (prices as of 2026-10-08). LangMem: create_memory_store_manager with default instructions, one invoke() per session, LangGraph InMemoryStore with OpenAI embeddings, store.search() with the default limit (10). Mem0: Open-source SDK with local Qdrant, NLP extras installed (spaCy, BM25). Mirrors Mem0's own LongMemEval harness: one add() per user+assistant pair, top_k=200 at search. Historical timestamps are platform-only, so the shared clock simulation supplies dates.
Which should I use, LangMem or Mem0?
If recall accuracy over long chat histories is what matters most, Mem0 did clearly better in this pilot. LangMem is cheaper, though: LangMem costs 1.5× less per 1,000 questions: $61.6 vs $93.0 for Mem0. LangMem is MIT and Mem0 is Apache-2.0 licensed. These are pilot numbers (30 questions each); the full 500-question run will narrow the intervals.
More comparisons
Other comparisons with LangMem
- Cognee vs LangMemCognee more accurate; LangMem 2.3× cheaper
- Full context vs LangMemFull context more accurate and 4.7× cheaper
- Graphiti vs LangMemGraphiti: pilot result withdrawn, rerun in progress
- Hindsight vs LangMemHindsight more accurate; LangMem 2.8× cheaper
- LangMem vs Plain RAGPlain RAG more accurate and 11× cheaper
Other comparisons with Mem0
- Cognee vs Mem0Statistically tied on accuracy at n=30; Mem0 1.5× cheaper
- Full context vs Mem0Tied on accuracy (83.3% each); Full context 7.1× cheaper
- Graphiti vs Mem0Graphiti: pilot result withdrawn, rerun in progress
- Hindsight vs Mem0Statistically tied on accuracy at n=30; Mem0 1.8× cheaper
- Mem0 vs Plain RAGStatistically tied on accuracy at n=30; Plain RAG 17× cheaper