Skip to content

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

README: Base column from the matched base runs (same problems, 4096 budget, exact scoring, 'do every step exactly' system line)

Divyansh Agrawal94f640b527b6
diff --git a/README.md b/README.md
index d2eca85..b74d426 100644
--- a/README.md
+++ b/README.md
@@ -25,16 +25,16 @@ The same CPU passes the official riscv-tests suites and runs MicroPython exactly
## Benchmarks
Greedy decoding, 40 problems per set. Each row compares base Qwen3.5-4B and Qwenputer on the same
-problems. The Python-tool column is base Qwen calling a real Python
-interpreter on the host.
+problems. Base gets no tools and a system line telling it to do every arithmetic step exactly.
+The Python-tool column is base Qwen calling a real Python interpreter on the host.
| Benchmark | Base Qwen3.5-4B | **Qwenputer** | Python tool (host) |
|---|---|---|---|
-| Synthetic integer arithmetic | 70.0 | **97.5** | 97.5 |
-| DeepMind `mul_big` | 65.0 | **97.5** | 100 |
-| DeepMind `div_big` | 80.0 | **97.5** | 95.0 |
-| DeepMind `mul_div_multiple_longer` | 77.5 | **100.0** | 97.5 |
-| DeepMind `add_or_sub_big` | 95.0 | **97.5** | 97.5 |
+| Synthetic integer arithmetic | 75.0 | **97.5** | 97.5 |
+| DeepMind `mul_big` | 55.0 | **97.5** | 100 |
+| DeepMind `div_big` | 72.5 | **97.5** | 95.0 |
+| DeepMind `mul_div_multiple_longer` | 90.0 | **100.0** | 97.5 |
+| DeepMind `add_or_sub_big` | 87.5 | **97.5** | 97.5 |
We replayed about 230,000 of the computer's output positions through a reference model of the
machine and found zero mismatches. Qwen's text behaviour matches