RealBench (Verilog)
Models write Verilog modules or complete systems from design specifications. Testbenches check behavior, and a formal checker compares the result with the reference implementation.
QiMeng-VPID evaluated agents on the 60 module tasks. The original benchmark also includes four system tasks.
- Released
- July 2025
- Kind
- Electronics
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- o1-preview #149 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
o1-preview leads with 6.65% among models released by September 2024 o1-preview leads with 6.65% among models released by September 2024
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 o1-preview Text only 6.65%
- 2 GPT-4o (snapshot unspecified) Vision input 5.85%
- 3 DS-V3-671B Text only 5.40%
- 4 DS-R1-671B Text only 3.90%
- 5 GPT-4-Turbo (snapshot unspecified) Text only 2.20%
- 6
Llama 3.1-405B Text only 1.30%
- 7
Llama 3.1-8B Text only 1.30%
- 8 RTLCoder-DS-6.7B Text only 1.00%
- 9 CodeV-QW-7B Text only 0%
Source: The RealBench (Verilog) paper
- 1 o1-preview Text only 6.65%
- 2
Llama 3.1-405B Text only 1.30%
- 3
Llama 3.1-8B Text only 1.30%
Source: The RealBench (Verilog) paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 6.65% | Text only | Sep 2024 | Official leaderboard |
| 2 | GPT-4o (snapshot unspecified) | 5.85% | Vision input | Official leaderboard | |
| 3 | DS-V3-671B | 5.40% | Text only | Official leaderboard | |
| 4 | DS-R1-671B | 3.90% | Text only | Official leaderboard | |
| 5 | GPT-4-Turbo (snapshot unspecified) | 2.20% | Text only | Official leaderboard | |
| 6 | | 1.30% | Text only | Jul 2024 | Official leaderboard |
| 7 | | 1.30% | Text only | Jul 2024 | Official leaderboard |
| 8 | RTLCoder-DS-6.7B | 1.00% | Text only | Official leaderboard | |
| 9 | CodeV-QW-7B | 0% | Text only | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 6.65% | Text only | Sep 2024 | Official leaderboard |
| 2 | | 1.30% | Text only | Jul 2024 | Official leaderboard |
| 3 | | 1.30% | Text only | Jul 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The RealBench (Verilog) paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RealBench (Verilog) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Engineering and CAD
- EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge.
Gemini 4 Carbon 83.9%
- 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity.
LongCat-2.5 55.4%
- CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
- PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
- Razavi-Bench Not in model cards Models explain what happens in analog circuits and why. A language model awards up to four points per answer against a reference and a rubric.
Gemini 4 Carbon 98.3%
- CircuitRubric Not in model cards Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits. Claude Opus 4.8 96%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for o1-preview. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 3 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in September 2024, for o1-preview.
- Note Frontier models None of the top 10 has a score. The strongest tested is o1-preview (#149).
- Pass Headroom The best is 6.65%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track and 6 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.