Benchmark Almanac

OmniRouting

GPT-5.5 28% leads since July 2026
Not in model cards

Models route copper traces between pads on printed circuit boards. The evaluator counts required nets that connect without design rule violations.

Nine models have one-shot scores and nine have agent scores. The two tables share eight models. The site links sample data.

Released
July 2026
Kind
Electronics
Level
University
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
In and out
Text, Images → Text, Actions
Interaction
Agentic
Environment
APIs and tools
Refresh
One fixed set
Run by
A host
In views
Agents, Vision
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
May 2026
Scores refreshed
November 20th, 2026
10
Models scored on its own leaderboard

GPT-5.5 leads with 28% among models released by May 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

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:

  1. 1 GPT-5.5 All Tools 28%
  2. 2 Claude Opus 4.8 All Tools 14.9%
  3. 3 GPT-5 mini Visualization 9.91%
  4. 4 Qwen3-235B-A22B Base 5.23%
  5. 5 Llama 4 Maverick Base 4.28%
  6. 6 Gemini 3.1 Pro Prerouting / Remake 4.08%
  7. 7 Mistral Large 3 Unlimited layer 3.68%
  8. 8 Qwen3.5-9B Visualization 1.85%
  9. 9 Gemini 2.5 Flash-Lite Sep 2025, Base 1.37%
  10. 10 Ministral 3 14B All Tools 0.96%

Source: Official OmniRouting leaderboard

#ModelScoreSettingDateSource
1 GPT-5.5 28% All Tools, Agent Apr 2026 Official leaderboard
2 Claude Opus 4.8 14.9% All Tools, Agent May 2026 Official leaderboard
3 GPT-5 mini 9.91% Visualization, Agent Aug 2025 Official leaderboard
4 Qwen3-235B-A22B 5.23% Base, One-shot Apr 2025 Official leaderboard
5 Llama 4 Maverick 4.28% Base, One-shot Apr 2025 Official leaderboard
6 Gemini 3.1 Pro 4.08% Prerouting / Remake, Agent Feb 2026 Official leaderboard
7 Mistral Large 3 3.68% Unlimited layer, One-shot Dec 2025 Official leaderboard
8 Qwen3.5-9B 1.85% Visualization, Agent Feb 2026 Official leaderboard
9 Gemini 2.5 Flash-Lite Sep 2025 1.37% Base, One-shot Sep 2025 Official leaderboard
10 Ministral 3 14B 0.96% All Tools, Agent Dec 2025 Official leaderboard

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.

Lowest effort to highest, light to dark
GPT-5.5 Agent
Visualizati… Routing Sco… All Tools
28%
Claude Opus 4.8 Agent
No Tools Routing Sco…
14.9%
Claude Opus 4.8 One-shot
Fewshot Prerouter
12.6%
GPT-5.5 One-shot
Unlimited l…
9.99%
GPT-5 mini Agent
All Tools Semantic In…
9.91%
GPT-5 mini One-shot
Fewshot
5.91%
Qwen3-235B-A22B One-shot
Fewshot Base
5.23%
Llama 4 Maverick One-shot
Fewshot Prerouter
4.28%
Gemini 3.1 Pro Agent
Routing Sco… Semantic In…
4.08%
Mistral Large 3 One-shot
Fewshot
3.68%
Qwen3.5-9B Agent
Semantic In…
1.85%
Llama 4 Maverick Agent
Routing Sco…
1.40%

Source: Official OmniRouting leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.5 All Tools Agent 28%
GPT-5.5 Routing Score Agent 24.8%
GPT-5.5 Prerouting / Remake Agent 22.6%
GPT-5.5 Semantic Input Agent 21.8%
GPT-5.5 No Tools Agent 21.7%
GPT-5.5 Visualization Agent 21%
Claude Opus 4.8 All Tools Agent 14.9%
Claude Opus 4.8 Prerouting / Remake Agent 14.1%
Claude Opus 4.8 Routing Score Agent 13.4%
Claude Opus 4.8 Base One-shot 12.6%
Claude Opus 4.8 Prerouter One-shot 12.5%
Claude Opus 4.8 Netclass detail One-shot 12.4%
Claude Opus 4.8 Unlimited layer One-shot 12.1%
Claude Opus 4.8 Semantic Input Agent 11.3%
Claude Opus 4.8 Visualization Agent 11.2%
Claude Opus 4.8 No Tools Agent 10.7%
Claude Opus 4.8 Fewshot One-shot 10.4%
GPT-5.5 Prerouter One-shot 9.99%
GPT-5 mini Visualization Agent 9.91%
GPT-5.5 Netclass detail One-shot 9.87%
GPT-5 mini No Tools Agent 9.86%
GPT-5 mini Routing Score Agent 9.85%
GPT-5.5 Fewshot One-shot 9.42%
GPT-5 mini Prerouting / Remake Agent 9.15%
GPT-5.5 Base One-shot 9.13%
GPT-5 mini Semantic Input Agent 9.08%
GPT-5.5 Unlimited layer One-shot 9.00%
GPT-5 mini All Tools Agent 6.82%
GPT-5 mini Prerouter One-shot 5.91%
GPT-5 mini Base One-shot 5.75%
GPT-5 mini Netclass detail One-shot 5.57%
Qwen3-235B-A22B Base One-shot 5.23%
GPT-5 mini Unlimited layer One-shot 5.12%
Qwen3-235B-A22B Unlimited layer One-shot 4.40%
Llama 4 Maverick Base One-shot 4.28%
Qwen3-235B-A22B Netclass detail One-shot 4.16%
GPT-5 mini Fewshot One-shot 4.09%
Gemini 3.1 Pro Prerouting / Remake Agent 4.08%
Mistral Large 3 Unlimited layer One-shot 3.68%
Mistral Large 3 Base One-shot 3.67%
Mistral Large 3 Netclass detail One-shot 3.67%
Qwen3-235B-A22B Prerouter One-shot 3.64%
Mistral Large 3 Prerouter One-shot 3.63%
Llama 4 Maverick Unlimited layer One-shot 3.58%
Llama 4 Maverick Netclass detail One-shot 3.37%
Mistral Large 3 Fewshot One-shot 3.13%
Llama 4 Maverick Prerouter One-shot 3.03%
Qwen3-235B-A22B Fewshot One-shot 2.90%
Gemini 3.1 Pro Semantic Input Agent 2.59%
Gemini 3.1 Pro No Tools Agent 2.20%
Qwen3.5-9B Visualization Agent 1.85%
Gemini 3.1 Pro Visualization Agent 1.82%
Llama 4 Maverick Prerouting / Remake Agent 1.40%
Qwen3.5-9B No Tools Agent 1.40%
Qwen3.5-9B Routing Score Agent 1.39%
Gemini 2.5 Flash-Lite Sep 2025 Base One-shot 1.37%
Gemini 2.5 Flash-Lite Sep 2025 Netclass detail One-shot 1.33%
Qwen3.5-9B Unlimited layer One-shot 1.28%
Qwen3.5-9B Base One-shot 1.24%
Gemini 3.1 Pro All Tools Agent 1.17%
Gemini 2.5 Flash-Lite Sep 2025 Unlimited layer One-shot 1.12%
Llama 4 Maverick All Tools Agent 1.11%
Qwen3.5-9B Netclass detail One-shot 1.10%
Qwen3.5-9B Fewshot One-shot 1.08%
Qwen3.5-9B Prerouter One-shot 1.07%
Ministral 3 14B All Tools Agent 0.96%
Ministral 3 14B Prerouting / Remake Agent 0.80%
Ministral 3 14B Routing Score Agent 0.79%
Gemini 2.5 Flash-Lite Sep 2025 Prerouter One-shot 0.77%
Gemini 3.1 Pro Base One-shot 0.71%
Ministral 3 14B Visualization Agent 0.49%
Gemini 2.5 Flash-Lite Sep 2025 Prerouting / Remake Agent 0.47%
Gemini 2.5 Flash-Lite Sep 2025 All Tools Agent 0.46%
Llama 4 Maverick Fewshot One-shot 0.44%
Gemini 3.1 Pro Routing Score Agent 0.44%
Ministral 3 14B No Tools Agent 0.39%
Gemini 3.1 Pro Netclass detail One-shot 0.37%
Llama 4 Maverick No Tools Agent 0.33%
Llama 4 Maverick Semantic Input Agent 0.27%
Gemini 2.5 Flash-Lite Sep 2025 No Tools Agent 0.27%
Ministral 3 14B Semantic Input Agent 0.27%
Llama 4 Maverick Visualization Agent 0.26%
Gemini 2.5 Flash-Lite Sep 2025 Routing Score Agent 0.23%
Llama 4 Maverick Routing Score Agent 0.20%
Qwen3.5-9B Prerouting / Remake Agent 0.15%
Qwen3.5-9B All Tools Agent 0.12%
Gemini 2.5 Flash-Lite Sep 2025 Visualization Agent 0.11%
Gemini 2.5 Flash-Lite Sep 2025 Fewshot One-shot 0.09%
Gemini 2.5 Flash-Lite Sep 2025 Semantic Input Agent 0.09%
Qwen3.5-9B Semantic Input Agent 0.09%
Qwen3-235B-A22B No Tools Agent 0%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Jul 2026
GPT-5.5 28%

Source: Official OmniRouting leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.5 GPT-5 mini Qwen3-235B-A22B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GPT-5.5 GPT-5 mini

Source: Official OmniRouting 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

All 112 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

8 of 10 checks pass, 2 warnings. 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 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 models we track.
  • Warning Newest score The newest came 6 months ago, in May 2026, for Claude Opus 4.8.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 28%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on omnieda.com: 91 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.

How we check