# Verilog generation on ChipBench-SC

Source: [Verilog generation on ChipBench-SC](<https://www.sota2.com/research/sota/verilog-generation-on-chipbench-sc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-14T07:35:15.850Z

Evaluation of model performance on generating Verilog code using the ChipBench-SC dataset, measured using Pass@1 and Pass@5 metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Verilog generation |
| Dataset (including any stated split) | ChipBench-SC |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Pass@1](<https://www.sota2.com/research/sota/verilog-generation-on-chipbench-sc.md?metric=Pass%401>): Higher is better; unit: PERCENT.

- [Pass@5](<https://www.sota2.com/research/sota/verilog-generation-on-chipbench-sc.md?metric=Pass%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| ChipMATE-Agents-9B | 36.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| ChipMATE-Agents-4B | 33.3 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| Claude Opus 4.7 | 31.3 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| GPT-5.5 | 30.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| CodeV-R1 | 30 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| ChipMATE-Verilog-9B | 30 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| DeepSeek R1 | 26.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| ChipMATE-Verilog-4B | 26.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| GPT-4o | 20 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| DeepSeek V4 | 18 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| DeepSeek Coder | 16.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| CodeV-R1 (distill) | 13.3 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| Qwen3.5-9B | 13.3 | Not recorded | 6a0556e7dbc836b87d828ae4 |
| Qwen3.5-4B | 6.7 | Not recorded | 6a0556e7dbc836b87d828ae4 |

### ChipMATE-Agents-9B

Pass@1: 36.7. Result ID: 6a057af647f34ce924ec2368.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"ChipMATE (Ours)","Size":"9B"}. This record does not assert independent reproduction.

### ChipMATE-Agents-4B

Pass@1: 33.3. Result ID: 6a057af647f34ce924ec2366.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"ChipMATE (Ours)","Size":"4B"}. This record does not assert independent reproduction.

### Claude Opus 4.7

Pass@1: 31.3. Result ID: 6a057af647f34ce924ec235d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":null}. This record does not assert independent reproduction.

### GPT-5.5

Pass@1: 30.7. Result ID: 6a057af647f34ce924ec235c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":null}. This record does not assert independent reproduction.

### CodeV-R1

Pass@1: 30. Result ID: 6a057af647f34ce924ec2362.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c29f.md>)

Recorded evaluation configuration: {"Type":"Specialized Models","Size":"7B"}. This record does not assert independent reproduction.

### ChipMATE-Verilog-9B

Pass@1: 30. Result ID: 6a057af647f34ce924ec2367.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"ChipMATE (Ours)","Size":"9B"}. This record does not assert independent reproduction.

### DeepSeek R1

Pass@1: 26.7. Result ID: 6a057af647f34ce924ec2360.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":"671B"}. This record does not assert independent reproduction.

### ChipMATE-Verilog-4B

Pass@1: 26.7. Result ID: 6a057af647f34ce924ec2365.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"ChipMATE (Ours)","Size":"4B"}. This record does not assert independent reproduction.

### GPT-4o

Pass@1: 20. Result ID: 6a057af647f34ce924ec235b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":null}. This record does not assert independent reproduction.

### DeepSeek V4

Pass@1: 18. Result ID: 6a057af647f34ce924ec235f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":"1.6T"}. This record does not assert independent reproduction.

### DeepSeek Coder

Pass@1: 16.7. Result ID: 6a057af647f34ce924ec235e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Foundation Models","Size":"236B"}. This record does not assert independent reproduction.

### CodeV-R1 (distill)

Pass@1: 13.3. Result ID: 6a057af647f34ce924ec2361.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c29f.md>)

Recorded evaluation configuration: {"Type":"Specialized Models","Size":"7B"}. This record does not assert independent reproduction.

### Qwen3.5-9B

Pass@1: 13.3. Result ID: 6a057af647f34ce924ec2364.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Base Models","Size":"9B"}. This record does not assert independent reproduction.

### Qwen3.5-4B

Pass@1: 6.7. Result ID: 6a057af647f34ce924ec2363.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ae4.md>)

Recorded evaluation configuration: {"Type":"Base Models","Size":"4B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
