GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
asm2c
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
asm2c
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Every answer is compiled with the target's toolchain and diffed by the asm2c scorer. A function counts only if the bytes are identical. If a function's prompt doesn't fit the context, or the model gives no output, it counts as a miss.
test: 234 held-out functions of doom, duke3d, quake, quake2 and zlib, whole translation units held out too. Every model gets the same functions, the same prompt and the same scorer.
| model | params | first-shot exact | pass@1 | best-of-9 | mean score |
|---|---|---|---|---|---|
| wyvern-1 | 7B | 25.2% | 24.1% | 31.2% | 48.7 |
| Qwen2.5-Coder-32B-Instruct | 32B | 9.0% | 9.2% | 16.2% | 27.0 |
| Qwen3-Coder-30B-A3B-Instruct | 30B MoE, 3B active | 7.7% | 8.5% | 9.4% | 14.3 |
| DeepSeek-Coder-V2-Lite-Instruct | 16B MoE, 2.4B active | 6.0% | 5.3% | 7.7% | 15.0 |
| Qwen2.5-Coder-7B-Instruct (base) | 7B | 5.1% | 4.6% | 6.4% | 14.5 |
fresh: 158 functions of heretic, sqlite and wolf3d, held out by stable hash before training. Same prompt, settings and scorer for every model.
| model | params | first-shot exact | pass@1 | best-of-9 | mean score |
|---|---|---|---|---|---|
| wyvern-1 | 7B | 9.5% | 8.6% | 13.3% | 27.8 |
| Qwen2.5-Coder-32B-Instruct | 32B | 2.5% | 2.8% | 5.7% | 21.1 |
| Qwen3-Coder-30B-A3B-Instruct | 30B MoE, 3B active | 1.3% | 1.1% | 1.3% | 2.0 |
| Qwen2.5-Coder-7B-Instruct (base) | 7B | 0.0% | 0.2% | 1.9% | 8.7 |
| DeepSeek-Coder-V2-Lite-Instruct | 16B MoE, 2.4B active | 0.0% | 0.2% | 1.3% | 10.2 |
prompt.py, greedy plus 8 samples, up to 1,536 new
tokens, a 16,384-token context, vLLM in bf16. The open models weren't tuned or given extra instructions.Raw numbers: bench/.
Every training pair is one function that an agent matched byte-for-byte during asm2c runs. The scorer recompiled the agent's C with the pinned toolchain and got identical bytes (relocations masked). An agent's own claim never admits a pair; only the scorer's re-check does. No synthetic pairs.
5,316 pairs (1,577,853 bytes of matched code), giving 7,760 training rows and about 23.5M tokens. The 2026-10-19 run and brogue pairs are weighted ×2, the earlier pairs ×1.
| target | program | licence | pairs | rows |
|---|---|---|---|---|
| doom | linuxdoom 1.10 | GPL-2.0 | 642 | 642 |
| duke3d | Duke Nukem 3D 1.5 (jfduke3d) | GPL-2.0 | 306 | 306 |
| quake | WinQuake 1.09 | GPL-2.0 | 897 | 897 |
| quake2 | Quake II game 3.21 | GPL-2.0 | 909 | 909 |
| zlib | zlib 1.2.13 | Zlib | 118 | 118 |
| brogue | Brogue CE | AGPL-3.0 | 383 | 766 |
| heretic | Heretic 1.3 | GPL-2.0 | 471 | 942 |
| sqlite | SQLite 3.54.1 | public domain | 1,198 | 2,396 |
| wolf3d | Wolf4SDL | GPL-2.0 or id Wolf3D licence | 392 | 784 |
| total | 5,316 | 7,760 |
dataset_stats.json.Log and config: logs/train.log, run_summary.json.
There are two turns: the system line names the toolchain, and the user turn carries one function. prompt.py builds
both exactly as in training. The chat template's default system line is the gcc-i686-o2 one, so a bare user turn
also works.
System:
text
You are asm2c, a matching decompiler. Write C source for ONE function so that it recompiles to byte-identical machine code (relocations masked) with the exact toolchain below. Reproduce the original control flow, types, operand order and statement order the compiler needs; do not optimize or restructure. Output only C: any needed declarations, then the function definition.toolchain: gcc-i686-o2compiler: gcc 15.2 -O2 (i686-linux-gnu)flags: -std=gnu89 -O2 -march=i686 -fno-pic -fno-pie -fno-asynchronous-unwind-tables -fno-stack-protector -fcf-protection=none -fcommon -fno-reorder-blocks-and-partition -fno-ipa-sra -fno-ipa-cp -fno-ipa-vrp -fno-ipa-bit-cp -fno-partial-inlining -fno-ipa-icf -fno-ipa-pure-const -fno-ipa-reference -fno-ipa-modref -fno-ipa-ra -warch: i386User (a fresh wolf3d function; the types: block is trimmed here):
text
function: FixedMul (25 bytes) · tu wl_utils.ccontext:proto: fixed FixedMul (fixed a, fixed b); /* wl_utils.h */includes: "wl_utils.h"sameTu: safe_malloc FixedDiv ReadShort ReadLong Error Help types:```ctypedef signed int __int32_t;typedef __int32_t int32_t;typedef int32_t fixed;``` target assembly:```asm# FixedMul (TU wl_utils.c, section .text, 25 bytes, binding global)# AT&T syntax. .Lxx = fn-relative branch targets; relocations shown symbolized:# "text" = string literal (.rodata.str), =0x.. = float/double constant (.rodata.cstN)FixedMul: /* 000 */ mov 0x4(%esp),%eax /* 004 */ imull 0x8(%esp) /* 008 */ add $0x8000,%eax /* 00d */ adc $0x0,%edx /* 010 */ mov %eax,%ecx /* 012 */ shrd $0x10,%edx,%ecx /* 016 */ mov %ecx,%eax /* 018 */ ret```wyvern-1, greedy (byte-exact):
c
#include "wl_utils.h" fixed FixedMul (fixed a, fixed b){ return (fixed)(((long long)a * (long long)b + 0x8000) >> 16);}The context lines are optional: proto, includes, callees, refs, data and sameTu. The types: block holds
the declarations the function needs. The asm is the function's listing in the format above. The model was trained
with this context present, so leaving it out is untested.
python
# hf download asm2c/wyvern-1-7b prompt.py --local-dir .import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom prompt import build_messages, extract_c tok = AutoTokenizer.from_pretrained("asm2c/wyvern-1-7b")model = AutoModelForCausalLM.from_pretrained("asm2c/wyvern-1-7b", dtype=torch.bfloat16, device_map="auto") pair = { "symbol": "FixedMul", "size": 25, "file": "wl_utils.c", "context": {"proto": "fixed FixedMul (fixed a, fixed b); /* wl_utils.h */", "includes": ['"wl_utils.h"'], "sameTu": ["safe_malloc", "FixedDiv", "ReadShort", "ReadLong", "Error", "Help"]}, "types": "typedef signed int __int32_t;\ntypedef __int32_t int32_t;\ntypedef int32_t fixed;", "asm": open("FixedMul.s").read(), # the listing, as above}ids = tok.apply_chat_template(build_messages(pair), add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**ids, max_new_tokens=2048) # greedy by default (generation_config.json)print(extract_c(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True)))Treat the output as a candidate. Compile it with the toolchain above and compare the function's bytes. Output that doesn't match can still compile. For a better hit rate, sample several answers (T 0.8, top-p 0.95) and keep the one that matches. On fresh, that takes 9.5% first-shot to 13.3% best-of-9.
The weights are Apache-2.0, the same as the base model. The training C reconstructs functions of the programs listed above, and each of those programs keeps its own licence.
You are asm2c, a matching decompiler. Write C source for ONE function so that it recompiles to byte-identical machine code (relocations masked) with the exact toolchain below. Reproduce the original control flow, types, operand order and statement order the compiler needs; do not optimize or restructure. Output only C: any needed declarations, then the function definition.toolchain: gcc-i686-o2compiler: gcc 15.2 -O2 (i686-linux-gnu)flags: -std=gnu89 -O2 -march=i686 -fno-pic -fno-pie -fno-asynchronous-unwind-tables -fno-stack-protector -fcf-protection=none -fcommon -fno-reorder-blocks-and-partition -fno-ipa-sra -fno-ipa-cp -fno-ipa-vrp -fno-ipa-bit-cp -fno-partial-inlining -fno-ipa-icf -fno-ipa-pure-const -fno-ipa-reference -fno-ipa-modref -fno-ipa-ra -warch: i386function: FixedMul (25 bytes) · tu wl_utils.ccontext:proto: fixed FixedMul (fixed a, fixed b); /* wl_utils.h */includes: "wl_utils.h"sameTu: safe_malloc FixedDiv ReadShort ReadLong Error Helptypes:```ctypedef signed int __int32_t;typedef __int32_t int32_t;typedef int32_t fixed;```target assembly:```asm# FixedMul (TU wl_utils.c, section .text, 25 bytes, binding global)# AT&T syntax. .Lxx = fn-relative branch targets; relocations shown symbolized:# "text" = string literal (.rodata.str), =0x.. = float/double constant (.rodata.cstN)FixedMul: /* 000 */ mov 0x4(%esp),%eax /* 004 */ imull 0x8(%esp) /* 008 */ add $0x8000,%eax /* 00d */ adc $0x0,%edx /* 010 */ mov %eax,%ecx /* 012 */ shrd $0x10,%edx,%ecx /* 016 */ mov %ecx,%eax /* 018 */ ret```#include "wl_utils.h" fixed FixedMul (fixed a, fixed b){ return (fixed)(((long long)a * (long long)b + 0x8000) >> 16);}# hf download asm2c/wyvern-1-7b prompt.py --local-dir .import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom prompt import build_messages, extract_c tok = AutoTokenizer.from_pretrained("asm2c/wyvern-1-7b")model = AutoModelForCausalLM.from_pretrained("asm2c/wyvern-1-7b", dtype=torch.bfloat16, device_map="auto") pair = { "symbol": "FixedMul", "size": 25, "file": "wl_utils.c", "context": {"proto": "fixed FixedMul (fixed a, fixed b); /* wl_utils.h */", "includes": ['"wl_utils.h"'], "sameTu": ["safe_malloc", "FixedDiv", "ReadShort", "ReadLong", "Error", "Help"]}, "types": "typedef signed int __int32_t;\ntypedef __int32_t int32_t;\ntypedef int32_t fixed;", "asm": open("FixedMul.s").read(), # the listing, as above}ids = tok.apply_chat_template(build_messages(pair), add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**ids, max_new_tokens=2048) # greedy by default (generation_config.json)print(extract_c(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True)))