ChironSign inStart free trial
BEAM benchmark, October 2026

125 million tokens in memory. The score didn't move.

BEAM is the public benchmark for AI memory: 200 questions about 10 million tokens of conversation. We added 115 million tokens of unrelated libraries and law to the same memory, and asked again.

Report

Written by Claude Fable 5.1, an AI model, from the run notes and grading output. Reviewed by James Youngquist, Mad Science Software. Published 22 October 2026, updated 26 October 2026.

BEAM scoreout of 100
Chiron, 10M tokens50.5, mean of three passes
Chiron, 125M tokens51.3, one pass
Mem0, 10M tokens48.6, as published
Read per question

17,000 → 19,000 tokens

at 10M and 125M in memory

Cost per question

2–3 cents

list price

Level with Mem0

AbilityChiron 10MChiron 125MMem0 10M
2Where Chiron leads
3Says when it doesn't knowAsked about something that was never said, it says so instead of inventing an answer.85.090.040.0
4Resolves contradictionsTwo things were said that can't both be true. It works out which one stands.48.150.032.5
5Keeps up with updatesA fact changed later in the conversation. It answers with the newer one.78.377.575.0
6Pulls out detailsNames, numbers and specifics from anywhere in the history.62.565.056.3
7Puts events in orderWhich happened first, and which came after.26.628.420.2
8About even
9SummarizesThe whole of a long thread in a few lines.47.952.346.9
10Reasons across sessionsAn answer that needs pieces from several conversations.25.823.026.1
11Reasons about timeHow long ago, how long between, and what was true when.16.220.016.3
12Where Mem0 leads
13Follows preferencesRemembers how you like things done, and does them that way.58.357.190.4
14Follows instructionsA rule set earlier in the conversation still applies later.55.850.082.5
15BEAM scoreMean of the ten abilities50.551.348.6

Scores out of 100. 10M is the mean of three passes, 125M one pass. Under two points is inside our own pass-to-pass spread.

Standing rules belong in a file the assistant reads every time, such as CLAUDE.md, not in recall. Chiron teams keep them there.

How we ran it

Benchmark

BEAM: Beyond a Million Tokens (Tavakoli and others, ICLR 2026). Ten conversations of about 10 million tokens, 20 questions each, two per ability.

Memory

One Chiron memory per conversation, cues by Claude Haiku 5.5. The 125M run added nine team libraries, the full United States Code and a quarter of the Code of Federal Regulations.

Answers

Claude Sonnet 5.5 with the Chiron plugin, a fresh container per question, BEAM's answering prompt.

Grading

BEAM's method: GPT-4.1-mini at temperature zero scores each point of the reference answer 0, ½ or 1; event ordering by rank correlation. The BEAM score is the mean of the ten abilities.

Passes

10M: 51.4, 49.6 and 50.4. 125M: 51.3.

Versions

Chiron 0.7.1 at 10M; at 125M, a development build with the search index from Chiron 0.9.1.

Mem0

As published in May 2026. Mem0 does not name its answering or judging model. Its per-ability figures are the only others we found.

Sources

Internal results, October 2026. Ask us for the run notes and grading scripts.

Questions

What is BEAM?

BEAM (Beyond a Million Tokens) is a public benchmark for long-term memory in AI assistants, published at ICLR 2026 by Tavakoli and colleagues. It holds 100 generated conversations of up to 10 million tokens each, and 2,000 questions that test ten memory abilities, from recalling a fact to putting events in order.

How does Chiron score on BEAM?

At the 10-million-token size, Chiron scores 50.5 out of 100, the mean of three complete passes, against 48.6 for Mem0's published result. A difference of under two points is inside the spread between our own passes, so we call the two level.

Does more memory lower the score?

No. With 115 million tokens of unrelated libraries and law added, 125 million tokens in all, Chiron scored 51.3 against 50.5. A question reads 17,000 to 19,000 tokens either way, so answers don't get slower or costlier as the memory grows.

Which models answered and graded?

Claude Sonnet 5.5 with the Chiron plugin answered, in a fresh container for every question, with BEAM's own answering prompt. Grading used BEAM's method: GPT-4.1-mini at temperature zero. Mem0 did not publish which models answered or graded its run.

Give your team's AI a memory that doesn't fill up.Start a free trial