AssertLLM2
Models write assertions for hardware specifications. A formal verifier checks which assertions hold, which logic they cover, and which deliberately introduced faults they detect.
ChipOmni ran DeepSeek on all 83 designs. The maintainers also release a 25-design subset spanning all 13 categories.
- Released
- May 2026
- Kind
- Electronics
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- GPT-5.2 #51 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
GPT-5.2 leads with 95% among models released by December 2025 GPT-5.2 leads with 95% among models released by December 2025
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the percentage of syntactically valid assertions, its first metric. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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 December 2025, 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 GPT-5.2 Average 95%
- 2 Claude Sonnet 4.5 Average 93%
- 3
Llama 4 Maverick Average 89.2%
- 4
DeepSeek-V3.2 Average 88.9%
- 5 Gemini-2.5-Pro (snapshot unspecified) Average 88.3%
- 6 Qwen3-Coder-Plus Average 77.9%
Source: The AssertLLM2 paper
- 1 GPT-5.2 Average 95%
- 2 Claude Sonnet 4.5 Average 93%
- 3
Llama 4 Maverick Average 89.2%
- 4
DeepSeek-V3.2 Average 88.9%
- 5 Qwen3-Coder-Plus Average 77.9%
Source: The AssertLLM2 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 95% | Average | Dec 2025 | Official leaderboard |
| 2 | Claude Sonnet 4.5 | 93% | Average | Sep 2025 | Official leaderboard |
| 3 | | 89.2% | Average | Apr 2025 | Official leaderboard |
| 4 | | 88.9% | Average | Dec 2025 | Official leaderboard |
| 5 | Gemini-2.5-Pro (snapshot unspecified) | 88.3% | Average | Official leaderboard | |
| 6 | Qwen3-Coder-Plus | 77.9% | Average | Sep 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 95% | Average | Dec 2025 | Official leaderboard |
| 2 | Claude Sonnet 4.5 | 93% | Average | Sep 2025 | Official leaderboard |
| 3 | | 89.2% | Average | Apr 2025 | Official leaderboard |
| 4 | | 88.9% | Average | Dec 2025 | Official leaderboard |
| 5 | Qwen3-Coder-Plus | 77.9% | Average | Sep 2025 | Official leaderboard |
Rankings by part
We read 7 parts from the benchmark’s paper, each ranking models on one part of the test, such as Syntax, Proven assertions and Syntactically correct assertions. Claude Sonnet 4.5 leads 5 of them, and GPT-5.2 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Syntax
5 models we track have a score here.
- 1 GPT-5.2 95%
- 2 Claude Sonnet 4.5 93%
- 3
Llama 4 Maverick 89.2%
- 4
DeepSeek-V3.2 88.9%
- 5 Qwen3-Coder-Plus 77.9%
Proven assertions
5 models we track have a score here.
- 1 GPT-5.2 65.0
- 2 Claude Sonnet 4.5 64.0
- 3
DeepSeek-V3.2 ↑1 38.0
- 4 Qwen3-Coder-Plus ↑1 25.0
- 5
Llama 4 Maverick ↓2 15.0
Syntactically correct assertions
5 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑1 115.0
- 2 GPT-5.2 ↓1 91.0
- 3
DeepSeek-V3.2 ↑1 65.0
- 4 Qwen3-Coder-Plus ↑1 53.0
- 5
Llama 4 Maverick ↓2 38.0
COI coverage
5 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑1 68.4%
- 2 GPT-5.2 ↓1 64.1%
- 3
DeepSeek-V3.2 ↑1 61.5%
- 4 Qwen3-Coder-Plus ↑1 56%
- 5
Llama 4 Maverick ↓2 49.4%
Proof coverage
5 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑1 29.7%
- 2 GPT-5.2 ↓1 28.6%
- 3
DeepSeek-V3.2 ↑1 25.7%
- 4 Qwen3-Coder-Plus ↑1 19.7%
- 5
Llama 4 Maverick ↓2 13.6%
Formal coverage
5 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑1 28.3%
- 2 GPT-5.2 ↓1 27.1%
- 3
DeepSeek-V3.2 ↑1 24.2%
- 4 Qwen3-Coder-Plus ↑1 18.6%
- 5
Llama 4 Maverick ↓2 12.7%
Bug kill ratio
5 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑1 16.3%
- 2
DeepSeek-V3.2 ↑2 15.3%
- 3 GPT-5.2 ↓2 14.9%
- 4 Qwen3-Coder-Plus ↑1 12.2%
- 5
Llama 4 Maverick ↓2 8.04%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The AssertLLM2 paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.2 | Average | 95% | |||
| GPT-5.2 | Union | 95% | |||
| Claude Sonnet 4.5 | Average | 93% | |||
| Claude Sonnet 4.5 | Union | 93% | |||
| Average | 89.2% | ||||
| Union | 89.2% | ||||
| Average | 88.9% | ||||
| Union | 88.9% | ||||
| Qwen3-Coder-Plus | Average | 77.9% | |||
| Qwen3-Coder-Plus | Union | 77.9% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The AssertLLM2 paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.2 | Average | 95% | |||
| GPT-5.2 | Union | 95% | |||
| Claude Sonnet 4.5 | Average | 93% | |||
| Claude Sonnet 4.5 | Union | 93% | |||
| Average | 89.2% | ||||
| Union | 89.2% | ||||
| Average | 88.9% | ||||
| Union | 88.9% | ||||
| Qwen3-Coder-Plus | Average | 77.9% | |||
| Qwen3-Coder-Plus | Union | 77.9% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The AssertLLM2 paper
Llama 4 Maverick on the official leaderboard passed 85% in April 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AssertLLM2 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
- Note Newest score The newest came 11 months ago, in December 2025, for GPT-5.2. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.2 (#51).
- Note Headroom Saturated. The best is 95%, past 85% since April 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 10 rows for models we track and 1 other entry 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.