ResearchTechnical note 1
Exact arithmetic inside a public language model
A public language model answers long arithmetic by predicting digits, and gets it wrong. Connected to METRON, AIDON’s exact co-processor, the same model, with its weights untouched, returns the exact answer.
- Measured
- 14 November 2026
- Model
- Qwen3-1.7B-Base
- Operations
- + − × <
- Record
- 118
At a glance
exact answers in every operation, up to 100 decimal digits, with METRON.
for the model alone in addition and subtraction from 50 digits, and in multiplication from 6.
weights changed. The public model is used exactly as published.
In plain words
Ask a language model to multiply two long numbers and it writes something that looks like a number. It is usually wrong. We gave the same model a small exact calculator of our own, called METRON. With it, every answer in the test was right.
For engineers
Qwen3-1.7B-Base, weights frozen, in two arms: alone, and with METRON attached by declared routing. Four operations, nine operand lengths from 1 to 100 decimal digits, 50 questions per cell, checked against an independent reference.
Why it matters
Exactness becomes a component that can be added to a model that already exists. No retraining, no larger model, no new data: the part that must not be wrong is handed to hardware-grade logic.
MTRMETRON is AIDON’s exact co-processor. It learns laws from data, proves them and runs them, alongside a neural model or on its own.
The bottleneck
Language models predict digits. They do not compute.
A language model produces a number the way it produces a sentence: one likely token after another. For short numbers that is often enough. As the numbers grow, the chance that every digit is right falls to zero.
In this test the public model alone answered 33 of 50 additions correctly at 20 digits and none at 50. In multiplication it was at zero from 6 digits.
Result
Same model, same questions. One difference.
- With METRON
- Model alone
Decimal digits per operand
Fig. 1 Exact answers out of 50 questions, by number of decimal digits per operand. The model and the questions are the same in both lines; the only difference is METRON.
| Digits | Addition | Subtraction | Multiplication | Comparison | ||||
|---|---|---|---|---|---|---|---|---|
| Alone | With | Alone | With | Alone | With | Alone | With | |
| 1 | 50 | 50 | 50 | 50 | 50 | 50 | 49 | 50 |
| 2 | 50 | 50 | 50 | 50 | 49 | 50 | 47 | 50 |
| 3 | 50 | 50 | 50 | 50 | 6 | 50 | 44 | 50 |
| 4 | 50 | 50 | 50 | 50 | 1 | 50 | 44 | 50 |
| 6 | 47 | 50 | 50 | 50 | 0 | 50 | 37 | 50 |
| 9 | 46 | 50 | 48 | 50 | 0 | 50 | 30 | 50 |
| 20 | 33 | 50 | 22 | 50 | 0 | 50 | 29 | 50 |
| 50 | 0 | 50 | 0 | 50 | 0 | 50 | 32 | 50 |
| 100 | 0 | 50 | 0 | 50 | 0 | 50 | 25 | 50 |
In hexadecimal, up to 128 digits (512 bits), the model with METRON answered 50 of 50 in every operation, except multiplication at 32 digits: 49 of 50.
Method
How METRON is connected
- Language modelreads the question and writes the expression
- METRONcomputes it bit by bit with frozen laws
- Answercarries the exact result
The model reads the question and writes the expression to be computed, as it would write any text.
The expression goes to METRON, which computes it bit by bit with laws learned once at 32 bits and then frozen.
The exact result returns to the answer. The model’s weights are never changed.
Controls
What was checked
Independent reference
METRON’s answer matched an independent reference computation in every cell of the test.
Scrambled laws
With its laws shuffled, METRON scored 0 in every cell from 2 digits up. The result comes from the laws, not from the wiring.
False triggers
0 in 2,000 lines of ordinary text. METRON only acts when there is something to compute.
Untouched weights
The model file had the same SHA-256 before and after the run.
Open questions
What this opens
- Placing METRON inside the model’s own computation, so that no routing step is needed.
- Extending the same exactness to other operations a language model cannot be trusted with.
Fields of application
Where it fits
- Financial and accounting agents, where a figure has to be right, not likely.
- Scientific and engineering assistants that work with long numbers.
- Embedded and safety-critical systems, where an answer cannot be approximate.
Record
How this result is kept
- Record
- 118
- Run
- 14 November 2026, 1 h 50 min
- Sample
- 50 questions per cell; 4 operations; 9 lengths from 1 to 100 decimal digits
- Measurement file
- SHA-256 c3f278f9fe4b4461f114d4e80dd7e2c58576e1c920d5c7a146656cf5f3eb51dc
Every figure on this page was read by a program from the raw measurement file, not typed. The fingerprint identifies that file: when it is disclosed, anyone can check that it is the same one.
Contact
Talk to the founders
Get in touch. We would be glad to share our ideas and walk you through the results, the proof and the measurements.