RadioBench
Models answer radio engineering questions and generate programs for software-defined radios. The authors measure successful execution, hardware deployment, and reception of the intended signal.
AlphaSignal covered RadioBench and its four metrics. The publication reports over 300,000 subscribers. The authors describe a planned public release.
- Made by
- Jiazhen Lei and the RadioMaster team
- Released
- June 2026
- Kind
- Electronics
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- A physical robot or device, Code sandbox
- Refresh
- One fixed set
- Run by
- A host
- In views
- Robotics
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- May 2026
- Scores refreshed
- November 20th, 2026
3 models share the top score of 97% among models released by May 2026
Best score per model 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 QAA Level 1 accuracy column, the first task column. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in May 2026, 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-5.5 97%
- 2
Qwen3.7-Max 97%
- 3 Claude Opus 4.8 97%
- 4
DeepSeek-V4-Pro 95%
Source: The RadioBench paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 97% | Apr 2026 | Official leaderboard | |
| 2 | | 97% | May 2026 | Official leaderboard | |
| 3 | Claude Opus 4.8 | 97% | May 2026 | Official leaderboard | |
| 4 | | 95% | Apr 2026 | 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 QAA Level 1, CPR Level 2 and CPR Level 3. GPT-5.5 leads 5 of them, and Claude Opus 4.8 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
QAA Level 1
4 models we track have a score here.
- 1 GPT-5.5 97%
- 2
Qwen3.7-Max 97%
- 3 Claude Opus 4.8 97%
- 4
DeepSeek-V4-Pro 95%
CPR Level 2
4 models we track have a score here.
- 1 Claude Opus 4.8 ↑2 89%
- 2 GPT-5.5 ↓1 88%
- 3
Qwen3.7-Max ↓1 88%
- 4
DeepSeek-V4-Pro 86%
CPR Level 3
4 models we track have a score here.
- 1 GPT-5.5 80%
- 2
Qwen3.7-Max 79%
- 3 Claude Opus 4.8 79%
- 4
DeepSeek-V4-Pro 77%
HDR Level 2
4 models we track have a score here.
- 1 GPT-5.5 87%
- 2 Claude Opus 4.8 ↑1 87%
- 3
Qwen3.7-Max ↓1 85%
- 4
DeepSeek-V4-Pro 84%
HDR Level 3
4 models we track have a score here.
- 1 Claude Opus 4.8 ↑2 78%
- 2 GPT-5.5 ↓1 77%
- 3
Qwen3.7-Max ↓1 77%
- 4
DeepSeek-V4-Pro 75%
SIR Level 2
4 models we track have a score here.
- 1 GPT-5.5 80%
- 2
Qwen3.7-Max 79%
- 3 Claude Opus 4.8 79%
- 4
DeepSeek-V4-Pro 77%
SIR Level 3
4 models we track have a score here.
- 1 GPT-5.5 68%
- 2 Claude Opus 4.8 ↑1 68%
- 3
Qwen3.7-Max ↓1 67%
- 4
DeepSeek-V4-Pro 66%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The RadioBench paper
GPT-5.5 on the official leaderboard passed 85% in April 2026
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 RadioBench 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
6 of 7 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (4 entries).
- Note Models scored Only 4 models we track.
- Note Newest score The newest came 6 months ago, in May 2026, for Claude Opus 4.8. 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-5.5 (#21).
- Note Headroom Saturated. The best is 97%, past 85% since April 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 4 rows for models we track 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.