CircuitRubric
Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits.
The maker compares 35 model labels on 125 circuits. Prompt detail and reasoning settings vary. Full credit requires matching the circuit structure and sizing ratios.
- Made by
- Manar El-Chammas
- Released
- June 2026
- Kind
- Electronics
- Level
- University
- 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
- GPT-5.5 #21 on the capability index
- Last model added
- June 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.8 leads with 96% among models released by June 2026 Claude Opus 4.8 leads with 96% among models released by June 2026
Best score per entry 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. 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 June 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
- 96.0 Claude Opus 4.8
- 95.2 GPT-5.5
- 95.2
Qwen3.7-Plus
- 94.4 Kimi K2.6
- 92.8 Claude Sonnet 4.6
- 92.0
DeepSeek-V4-Pro
- 92.0
Qwen3.7-Max
- 91.2 GLM-5.1
- 89.6
Gemini 3.1 Pro
- 89.6
MiniMax-M3
- 88.0 Claude Haiku 4.5
- 85.6
Llama 4 Maverick
- 85.6 GLM-4.5
- 85.6
DeepSeek-V4-Flash
- 84.8
Llama 3.3 70B Instruct
- 82.4 Kimi K2
- 78.4 gpt-oss-20b
- 76.8 deepseek/deepseek-chat-v3-0324
- 71.2 Claude Opus 4.7
- 68.8 qwen3.5:latest
- 68.0 phi4:14b
- 66.4
Qwen2.5-Coder (7B)
- 64.0 qwen3:30b-a3b-instruct-2507-q4_K_M
- 59.2
Qwen3-235B-A22B-Instruct
- 58.4
Gemini 3.5 Flash
- 54.4
Qwen3-14B
- 45.6 deepseek-coder-v2:16b
- 44.8 GLM-5.2
- 42.4 Qwen2.5-Coder-14B
- 34.4
Gemma 3 12B
- 27.2
Llama 3.1-8B
- 24.0
Gemma 2 9B
- 16.0 granite3.1-dense:8b
- 12.8
Gemma 4 31B IT
- 0.80 deepseek-r1:14b
- 1 Claude Opus 4.8 spec, conventions, run fe-opus-spec-conventions 96%
- 2 GPT-5.5 spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports 95.2%
- 3
Qwen3.7-Plus spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports 95.2%
- 4 Kimi K2.6 spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports 94.4%
- 5 Claude Sonnet 4.6 spec, conventions, run fe-sonnet-spec-conventions 92.8%
- 6
DeepSeek-V4-Pro spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports 92%
- 7
Qwen3.7-Max spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports 92%
- 8 GLM-5.1 spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports 91.2%
- 9
Gemini 3.1 Pro short, conventions, run 20260623-020043-gemini-3.1-pro 89.6%
- 10
MiniMax-M3 spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports 89.6%
- 11 Claude Haiku 4.5 spec, strict_ports, run fe-haiku-spec-strict_ports 88%
- 12
Llama 4 Maverick spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports 85.6%
- 13 GLM-4.5 spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports 85.6%
- 14
DeepSeek-V4-Flash spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports 85.6%
- 15
Llama 3.3 70B Instruct spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports 84.8%
- 16 Kimi K2 Sep 2025, spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports 82.4%
- 17 gpt-oss-20b spec, strict_ports, run lb-gptoss-20b-spec-strict_ports 78.4%
- 18 deepseek/deepseek-chat-v3-0324 spec, strict_ports, run or-deepseek-v3-2025-spec-strict_ports 76.8%
- 19 Claude Opus 4.7 short, topology_ports, high, run fe-opus47-high-short-topology_ports 71.2%
- 20 qwen3.5:latest spec, strict_ports, run 20260613-045341-qwen3.5 68.8%
- 21 phi4:14b spec, strict_ports, run lb-phi4-spec-strict_ports 68%
- 22
Qwen2.5-Coder (7B) spec, topology_ports, run 20260613-042138-qwen2.5-coder 66.4%
- 23 qwen3:30b-a3b-instruct-2507-q4_K_M spec, strict_ports, run 30b-spec-strict_ports 64%
- 24
Qwen3-235B-A22B-Instruct Jul 2025, spec, strict_ports, run or-qwen3-235b-spec-strict_ports 59.2%
- 25
Gemini 3.5 Flash short, topology_ports, run 20260622-224557-gemini-3.5-flash 58.4%
- 26
Qwen3-14B spec, topology, run lb-qwen3-14b-spec-topology 54.4%
- 27 deepseek-coder-v2:16b spec, strict_ports, run lb-dscoder-v2-spec-strict_ports 45.6%
- 28 GLM-5.2 short, topology_ports, run or-glm-5.2-short-topology_ports 44.8%
- 29 Qwen2.5-Coder-14B spec, strict_ports, run lb-coder14b-spec-strict_ports 42.4%
- 30
Gemma 3 12B spec, strict_ports, run lb-gemma3-spec-strict_ports 34.4%
- 31
Llama 3.1-8B spec, strict_ports, run 20260613-045341-llama3.1 27.2%
- 32
Gemma 2 9B spec, topology_ports, run lb-gemma2-spec-topology_ports 24%
- 33 granite3.1-dense:8b spec, strict_ports, run 20260613-045341-granite3.1 16%
- 34
Gemma 4 31B IT short, topology_ports, run 20260622-224557-gemma-4-31b 12.8%
- 35 deepseek-r1:14b short, strict_ports, run lb-thinkfalse-deepseek-r1-14b-short-strict_ports 0.80%
Source: Official CircuitRubric leaderboard
- 96.0 Claude Opus 4.8
- 95.2 GPT-5.5
- 95.2
Qwen3.7-Plus
- 94.4 Kimi K2.6
- 92.8 Claude Sonnet 4.6
- 92.0
DeepSeek-V4-Pro
- 92.0
Qwen3.7-Max
- 91.2 GLM-5.1
- 89.6
Gemini 3.1 Pro
- 89.6
MiniMax-M3
- 88.0 Claude Haiku 4.5
- 85.6
Llama 4 Maverick
- 85.6 GLM-4.5
- 85.6
DeepSeek-V4-Flash
- 84.8
Llama 3.3 70B Instruct
- 82.4 Kimi K2
- 78.4 gpt-oss-20b
- 71.2 Claude Opus 4.7
- 66.4
Qwen2.5-Coder (7B)
- 59.2
Qwen3-235B-A22B-Instruct
- 58.4
Gemini 3.5 Flash
- 54.4
Qwen3-14B
- 44.8 GLM-5.2
- 42.4 Qwen2.5-Coder-14B
- 34.4
Gemma 3 12B
- 27.2
Llama 3.1-8B
- 24.0
Gemma 2 9B
- 12.8
Gemma 4 31B IT
- 1 Claude Opus 4.8 spec, conventions, run fe-opus-spec-conventions 96%
- 2 GPT-5.5 spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports 95.2%
- 3
Qwen3.7-Plus spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports 95.2%
- 4 Kimi K2.6 spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports 94.4%
- 5 Claude Sonnet 4.6 spec, conventions, run fe-sonnet-spec-conventions 92.8%
- 6
DeepSeek-V4-Pro spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports 92%
- 7
Qwen3.7-Max spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports 92%
- 8 GLM-5.1 spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports 91.2%
- 9
Gemini 3.1 Pro short, conventions, run 20260623-020043-gemini-3.1-pro 89.6%
- 10
MiniMax-M3 spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports 89.6%
- 11 Claude Haiku 4.5 spec, strict_ports, run fe-haiku-spec-strict_ports 88%
- 12
Llama 4 Maverick spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports 85.6%
- 13 GLM-4.5 spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports 85.6%
- 14
DeepSeek-V4-Flash spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports 85.6%
- 15
Llama 3.3 70B Instruct spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports 84.8%
- 16 Kimi K2 Sep 2025, spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports 82.4%
- 17 gpt-oss-20b spec, strict_ports, run lb-gptoss-20b-spec-strict_ports 78.4%
- 18 Claude Opus 4.7 short, topology_ports, high, run fe-opus47-high-short-topology_ports 71.2%
- 19
Qwen2.5-Coder (7B) spec, topology_ports, run 20260613-042138-qwen2.5-coder 66.4%
- 20
Qwen3-235B-A22B-Instruct Jul 2025, spec, strict_ports, run or-qwen3-235b-spec-strict_ports 59.2%
- 21
Gemini 3.5 Flash short, topology_ports, run 20260622-224557-gemini-3.5-flash 58.4%
- 22
Qwen3-14B spec, topology, run lb-qwen3-14b-spec-topology 54.4%
- 23 GLM-5.2 short, topology_ports, run or-glm-5.2-short-topology_ports 44.8%
- 24 Qwen2.5-Coder-14B spec, strict_ports, run lb-coder14b-spec-strict_ports 42.4%
- 25
Gemma 3 12B spec, strict_ports, run lb-gemma3-spec-strict_ports 34.4%
- 26
Llama 3.1-8B spec, strict_ports, run 20260613-045341-llama3.1 27.2%
- 27
Gemma 2 9B spec, topology_ports, run lb-gemma2-spec-topology_ports 24%
- 28
Gemma 4 31B IT short, topology_ports, run 20260622-224557-gemma-4-31b 12.8%
Source: Official CircuitRubric leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 96% | spec, conventions, run fe-opus-spec-conventions, anthropic | May 2026 | Official leaderboard |
| 2 | GPT-5.5 | 95.2% | spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 3 | | 95.2% | spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports, openai | Jun 2026 | Official leaderboard |
| 4 | Kimi K2.6 | 94.4% | spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 5 | Claude Sonnet 4.6 | 92.8% | spec, conventions, run fe-sonnet-spec-conventions, anthropic | Feb 2026 | Official leaderboard |
| 6 | | 92% | spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 7 | | 92% | spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports, openai | May 2026 | Official leaderboard |
| 8 | GLM-5.1 | 91.2% | spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 9 | | 89.6% | short, conventions, run 20260623-020043-gemini-3.1-pro, openai | Feb 2026 | Official leaderboard |
| 10 | | 89.6% | spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports, openai | Jun 2026 | Official leaderboard |
| 11 | Claude Haiku 4.5 | 88% | spec, strict_ports, run fe-haiku-spec-strict_ports, anthropic | Oct 2025 | Official leaderboard |
| 12 | | 85.6% | spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports, openai | Apr 2025 | Official leaderboard |
| 13 | GLM-4.5 | 85.6% | spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports, openai | Aug 2025 | Official leaderboard |
| 14 | | 85.6% | spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 15 | | 84.8% | spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports, openai | Dec 2024 | Official leaderboard |
| 16 | Kimi K2 Sep 2025 | 82.4% | spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports, openai | Sep 2025 | Official leaderboard |
| 17 | gpt-oss-20b | 78.4% | spec, strict_ports, run lb-gptoss-20b-spec-strict_ports, ollama | Aug 2025 | Official leaderboard |
| 18 | deepseek/deepseek-chat-v3-0324 | 76.8% | spec, strict_ports, run or-deepseek-v3-2025-spec-strict_ports, openai | Official leaderboard | |
| 19 | Claude Opus 4.7 | 71.2% | short, topology_ports, high, run fe-opus47-high-short-topology_ports, anthropic | Apr 2026 | Official leaderboard |
| 20 | qwen3.5:latest | 68.8% | spec, strict_ports, run 20260613-045341-qwen3.5, ollama | Official leaderboard | |
| 21 | phi4:14b | 68% | spec, strict_ports, run lb-phi4-spec-strict_ports, ollama | Official leaderboard | |
| 22 | | 66.4% | spec, topology_ports, run 20260613-042138-qwen2.5-coder, ollama | Sep 2024 | Official leaderboard |
| 23 | qwen3:30b-a3b-instruct-2507-q4_K_M | 64% | spec, strict_ports, run 30b-spec-strict_ports, ollama | Official leaderboard | |
| 24 | | 59.2% | spec, strict_ports, run or-qwen3-235b-spec-strict_ports, openai | Jul 2025 | Official leaderboard |
| 25 | | 58.4% | short, topology_ports, run 20260622-224557-gemini-3.5-flash, openai | May 2026 | Official leaderboard |
| 26 | | 54.4% | spec, topology, run lb-qwen3-14b-spec-topology, ollama | Apr 2025 | Official leaderboard |
| 27 | deepseek-coder-v2:16b | 45.6% | spec, strict_ports, run lb-dscoder-v2-spec-strict_ports, ollama | Official leaderboard | |
| 28 | GLM-5.2 | 44.8% | short, topology_ports, run or-glm-5.2-short-topology_ports, openai | Jun 2026 | Official leaderboard |
| 29 | Qwen2.5-Coder-14B | 42.4% | spec, strict_ports, run lb-coder14b-spec-strict_ports, ollama | Sep 2024 | Official leaderboard |
| 30 | | 34.4% | spec, strict_ports, run lb-gemma3-spec-strict_ports, ollama | Mar 2025 | Official leaderboard |
| 31 | | 27.2% | spec, strict_ports, run 20260613-045341-llama3.1, ollama | Jul 2024 | Official leaderboard |
| 32 | | 24% | spec, topology_ports, run lb-gemma2-spec-topology_ports, ollama | Jun 2024 | Official leaderboard |
| 33 | granite3.1-dense:8b | 16% | spec, strict_ports, run 20260613-045341-granite3.1, ollama | Official leaderboard | |
| 34 | | 12.8% | short, topology_ports, run 20260622-224557-gemma-4-31b, openai | Apr 2026 | Official leaderboard |
| 35 | deepseek-r1:14b | 0.80% | short, strict_ports, run lb-thinkfalse-deepseek-r1-14b-short-strict_ports, ollama | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 96% | spec, conventions, run fe-opus-spec-conventions, anthropic | May 2026 | Official leaderboard |
| 2 | GPT-5.5 | 95.2% | spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 3 | | 95.2% | spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports, openai | Jun 2026 | Official leaderboard |
| 4 | Kimi K2.6 | 94.4% | spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 5 | Claude Sonnet 4.6 | 92.8% | spec, conventions, run fe-sonnet-spec-conventions, anthropic | Feb 2026 | Official leaderboard |
| 6 | | 92% | spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 7 | | 92% | spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports, openai | May 2026 | Official leaderboard |
| 8 | GLM-5.1 | 91.2% | spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 9 | | 89.6% | short, conventions, run 20260623-020043-gemini-3.1-pro, openai | Feb 2026 | Official leaderboard |
| 10 | | 89.6% | spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports, openai | Jun 2026 | Official leaderboard |
| 11 | Claude Haiku 4.5 | 88% | spec, strict_ports, run fe-haiku-spec-strict_ports, anthropic | Oct 2025 | Official leaderboard |
| 12 | | 85.6% | spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports, openai | Apr 2025 | Official leaderboard |
| 13 | GLM-4.5 | 85.6% | spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports, openai | Aug 2025 | Official leaderboard |
| 14 | | 85.6% | spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports, openai | Apr 2026 | Official leaderboard |
| 15 | | 84.8% | spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports, openai | Dec 2024 | Official leaderboard |
| 16 | Kimi K2 Sep 2025 | 82.4% | spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports, openai | Sep 2025 | Official leaderboard |
| 17 | gpt-oss-20b | 78.4% | spec, strict_ports, run lb-gptoss-20b-spec-strict_ports, ollama | Aug 2025 | Official leaderboard |
| 18 | Claude Opus 4.7 | 71.2% | short, topology_ports, high, run fe-opus47-high-short-topology_ports, anthropic | Apr 2026 | Official leaderboard |
| 19 | | 66.4% | spec, topology_ports, run 20260613-042138-qwen2.5-coder, ollama | Sep 2024 | Official leaderboard |
| 20 | | 59.2% | spec, strict_ports, run or-qwen3-235b-spec-strict_ports, openai | Jul 2025 | Official leaderboard |
| 21 | | 58.4% | short, topology_ports, run 20260622-224557-gemini-3.5-flash, openai | May 2026 | Official leaderboard |
| 22 | | 54.4% | spec, topology, run lb-qwen3-14b-spec-topology, ollama | Apr 2025 | Official leaderboard |
| 23 | GLM-5.2 | 44.8% | short, topology_ports, run or-glm-5.2-short-topology_ports, openai | Jun 2026 | Official leaderboard |
| 24 | Qwen2.5-Coder-14B | 42.4% | spec, strict_ports, run lb-coder14b-spec-strict_ports, ollama | Sep 2024 | Official leaderboard |
| 25 | | 34.4% | spec, strict_ports, run lb-gemma3-spec-strict_ports, ollama | Mar 2025 | Official leaderboard |
| 26 | | 27.2% | spec, strict_ports, run 20260613-045341-llama3.1, ollama | Jul 2024 | Official leaderboard |
| 27 | | 24% | spec, topology_ports, run lb-gemma2-spec-topology_ports, ollama | Jun 2024 | Official leaderboard |
| 28 | | 12.8% | short, topology_ports, run 20260622-224557-gemma-4-31b, openai | Apr 2026 | Official leaderboard |
More effort adds a median 40 points
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: Official CircuitRubric leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.8 | spec, conventions, run fe-opus-spec-conventions | anthropic | 96% | 212 | |
| GPT-5.5 | spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports | openai | 95.2% | ||
| spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports | openai | 95.2% | 55 | ||
| Kimi K2.6 | spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports | openai | 94.4% | 163 | |
| Claude Sonnet 4.6 | spec, conventions, run fe-sonnet-spec-conventions | anthropic | 92.8% | 325 | |
| Claude Opus 4.8 | short, conventions, xhigh, run fe-opus48-xhigh-short-conventions | anthropic | 92.8% | 1,777 | |
| spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports | openai | 92% | 181 | ||
| spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports | openai | 92% | |||
| Claude Sonnet 4.6 | spec, strict_ports, run fe-sonnet-spec-strict_ports | anthropic | 91.2% | 302 | |
| GLM-5.1 | spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports | openai | 91.2% | 27 | |
| short, conventions, run 20260623-020043-gemini-3.1-pro | openai | 89.6% | 1,546 | ||
| spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports | openai | 89.6% | 82 | ||
| short, topology_ports, run 20260622-224557-gemini-3.1-pro | openai | 88.8% | 2,024 | ||
| Claude Haiku 4.5 | spec, strict_ports, run fe-haiku-spec-strict_ports | anthropic | 88% | 200 | |
| spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports | openai | 85.6% | |||
| GLM-4.5 | spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports | openai | 85.6% | 680 | |
| GPT-5.5 | short, conventions, run or-gpt-5.5-closed-short-conventions | openai | 85.6% | 882 | |
| spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports | openai | 85.6% | |||
| spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports | openai | 84.8% | |||
| Claude Haiku 4.5 | spec, conventions, run fe-haiku-spec-conventions | anthropic | 84.8% | 239 | |
| short, strict_ports, run 20260623-020041-gemini-3.1-pro | openai | 84.8% | 1,641 | ||
| short, topology_ports, low, run gemini-3.1-pro-low-short-topology_ports | openai | 84.8% | 828 | ||
| GPT-5.5 | verbose, strict_ports, run or-gpt-5.5-closed-verbose-strict_ports | openai | 84.8% | 130 | |
| Claude Opus 4.8 | short, topology_ports, max, run fe-opus48-max-short-topology_ports | anthropic | 84% | 4,289 | |
| Kimi K2 Sep 2025 | spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports | openai | 82.4% | 1 | |
| Claude Opus 4.8 | short, topology_ports, xhigh, run fe-opus48-xhigh-short-topology_ports | anthropic | 82.4% | 114 | |
| verbose, strict_ports, run or-qwen3.7-max-2026-verbose-strict_ports | openai | 79.2% | 3,755 | ||
| gpt-oss-20b | spec, strict_ports, run lb-gptoss-20b-spec-strict_ports | ollama | 78.4% | 240 | |
| GPT-5.5 | short, topology_ports, xhigh, run or-gpt-5.5-xhigh-short-topology_ports | openai | 77.6% | 2,968 | |
| Claude Opus 4.8 | short, strict_ports, xhigh, run fe-opus48-xhigh-short-strict_ports | anthropic | 77.6% | 1,788 | |
| gpt-oss-20b | spec, topology_ports, run lb-gptoss-20b-spec-topology_ports | ollama | 75.2% | 268 | |
| Kimi K2.6 | verbose, strict_ports, run or-kimi-k2.6-2026-verbose-strict_ports | openai | 75.2% | 3,255 | |
| GPT-5.5 | short, topology_ports, run or-gpt-5.5-short-topology_ports | openai | 75.2% | 1,044 | |
| Claude Opus 4.8 | short, topology_ports, high, run fe-opus48-high-short-topology_ports | anthropic | 75.2% | 896 | |
| Claude Opus 4.8 | verbose, conventions, run fe-opus-verbose-conventions | anthropic | 75.2% | 308 | |
| Claude Opus 4.8 | verbose, strict_ports, run fe-opus-verbose-strict_ports | anthropic | 75.2% | 301 | |
| GLM-5.1 | verbose, strict_ports, run or-glm-5.1-2026-verbose-strict_ports | openai | 72% | 545 | |
| GPT-5.5 | short, strict_ports, run or-gpt-5.5-closed-short-strict_ports | openai | 72% | 981 | |
| Claude Opus 4.7 | short, topology_ports, high, run fe-opus47-high-short-topology_ports | anthropic | 71.2% | 1,065 | |
| Claude Opus 4.8 | short, conventions, run fe-opus-short-conventions | anthropic | 68.8% | 303 | |
| Claude Opus 4.7 | short, conventions, run fe-opus47-short-conventions | anthropic | 68% | 277 | |
| Kimi K2.6 | short, conventions, run or-kimi-k2.6-2026-short-conventions | openai | 68% | 1,966 | |
| spec, topology_ports, run 20260613-042138-qwen2.5-coder | ollama | 66.4% | 114 | ||
| Kimi K2.6 | short, strict_ports, run or-kimi-k2.6-2026-short-strict_ports | openai | 66.4% | 774 | |
| Claude Sonnet 4.6 | verbose, conventions, run fe-sonnet-verbose-conventions | anthropic | 65.6% | 587 | |
| Claude Opus 4.7 | short, strict_ports, run fe-opus47-short-strict_ports | anthropic | 65.6% | 294 | |
| short, strict_ports, run or-qwen3.7-max-2026-short-strict_ports | openai | 65.6% | 3,546 | ||
| spec, topology_ports, run lb-coder-spec-topology_ports | ollama | 64.8% | 115 | ||
| Claude Sonnet 4.6 | verbose, strict_ports, run fe-sonnet-verbose-strict_ports | anthropic | 64.8% | 589 | |
| GLM-5.1 | short, conventions, run or-glm-5.1-2026-short-conventions | openai | 64% | 512 | |
| spec, strict_ports, run 20260613-045341-qwen2.5-coder | ollama | 63.2% | 111 | ||
| GLM-5.1 | short, topology_ports, run or-glm-5.1-short-topology_ports | openai | 63.2% | 3,958 | |
| GLM-5.1 | short, strict_ports, run or-glm-5.1-2026-short-strict_ports | openai | 62.4% | 1,421 | |
| short, conventions, run or-qwen3.7-max-2026-short-conventions | openai | 62.4% | 3,840 | ||
| Claude Opus 4.8 | short, topology_ports, xhigh, run fe-opus48-xhigh-nothink-short-topology_ports | anthropic | 62.4% | 25 | |
| spec, strict_ports, run lb-coder-spec-strict_ports | ollama | 61.6% | 112 | ||
| Claude Opus 4.7 | short, topology_ports, run fe-opus47-short-topology_ports | anthropic | 61.6% | 344 | |
| verbose, strict_ports, run or-qwen3.7-plus-2026-verbose-strict_ports | openai | 61.6% | 5,455 | ||
| spec, strict_ports, run or-qwen3-235b-spec-strict_ports | openai | 59.2% | 151 | ||
| Claude Opus 4.8 | short, strict_ports, run fe-opus-short-strict_ports | anthropic | 59.2% | 270 | |
| verbose, strict_ports, run or-deepseek-v4-pro-2026-verbose-strict_ports | openai | 58.4% | 671 | ||
| short, topology_ports, run 20260622-224557-gemini-3.5-flash | openai | 58.4% | 2,494 | ||
| Kimi K2.6 | short, topology_ports, run or-kimi-k2.6-short-topology_ports | openai | 57.6% | 7,603 | |
| verbose, strict_ports, run or-minimax-m3-2026-verbose-strict_ports | openai | 55.2% | 2,183 | ||
| spec, topology, run lb-qwen3-14b-spec-topology | ollama | 54.4% | 178 | ||
| Claude Opus 4.8 | short, topology_ports, run fe-opus48-short-topology_ports | anthropic | 53.6% | 338 | |
| spec, strict_ports, run lb-qwen3-14b-spec-strict_ports | ollama | 52% | 135 | ||
| short, conventions, run or-deepseek-v4-pro-2026-short-conventions | openai | 52% | 452 | ||
| short, strict_ports, run or-deepseek-v4-pro-2026-short-strict_ports | openai | 52% | 731 | ||
| short, topology_ports, run or-qwen3.7-max-short-topology_ports | openai | 52% | 4,934 | ||
| short, conventions, run or-qwen3.7-plus-2026-short-conventions | openai | 52% | 4,854 | ||
| spec, conventions, run lb-qwen3-14b-spec-conventions | ollama | 48.8% | 166 | ||
| short, strict_ports, run or-qwen3.7-plus-2026-short-strict_ports | openai | 48.8% | 4,755 | ||
| GLM-4.5 | verbose, strict_ports, run or-glm-4.5-2025-verbose-strict_ports | openai | 48% | 4,761 | |
| Claude Sonnet 4.6 | short, strict_ports, run fe-sonnet-short-strict_ports | anthropic | 48% | 599 | |
| short, conventions, run or-minimax-m3-2026-short-conventions | openai | 45.6% | 2,476 | ||
| short, strict_ports, run or-minimax-m3-2026-short-strict_ports | openai | 45.6% | 1,648 | ||
| GLM-5.2 | short, topology_ports, run or-glm-5.2-short-topology_ports | openai | 44.8% | 4,045 | |
| Claude Sonnet 4.6 | short, conventions, run fe-sonnet-short-conventions | anthropic | 44% | 594 | |
| Qwen2.5-Coder-14B | spec, strict_ports, run lb-coder14b-spec-strict_ports | ollama | 42.4% | 166 | |
| gpt-oss-20b | spec, topology, run lb-gptoss-20b-spec-topology | ollama | 41.6% | 270 | |
| verbose, strict_ports, run or-deepseek-v4-flash-2026-verbose-strict_ports | openai | 41.6% | |||
| Qwen2.5-Coder-14B | spec, conventions, run lb-coder14b-spec-conventions | ollama | 40% | 168 | |
| short, topology_ports, run or-deepseek-v4-pro-short-topology_ports | openai | 40% | 2,045 | ||
| spec, strict_ports, run lb-gemma3-spec-strict_ports | ollama | 34.4% | 222 | ||
| GLM-4.5 | short, strict_ports, run or-glm-4.5-2025-short-strict_ports | openai | 33.6% | 5,574 | |
| short, strict_ports, run or-deepseek-v4-flash-2026-short-strict_ports | openai | 33.6% | 863 | ||
| short, conventions, run or-deepseek-v4-flash-2026-short-conventions | openai | 32.8% | 1,320 | ||
| Qwen2.5-Coder-14B | spec, topology, run lb-coder14b-spec-topology | ollama | 32% | 196 | |
| gpt-oss-20b | spec, conventions, run lb-gptoss-20b-spec-conventions | ollama | 32% | 258 | |
| Qwen2.5-Coder-14B | spec, topology_ports, run lb-coder14b-spec-topology_ports | ollama | 30.4% | 99 | |
| spec, topology_ports, run lb-qwen3-14b-spec-topology_ports | ollama | 30.4% | 122 | ||
| Claude Haiku 4.5 | verbose, strict_ports, run fe-haiku-verbose-strict_ports | anthropic | 30.4% | 540 | |
| spec, strict_ports, run 20260613-045341-llama3.1 | ollama | 27.2% | 159 | ||
| GLM-4.5 | short, conventions, run or-glm-4.5-2025-short-conventions | openai | 26.4% | 6,048 | |
| Claude Haiku 4.5 | verbose, conventions, run fe-haiku-verbose-conventions | anthropic | 26.4% | 552 | |
| Kimi K2 Sep 2025 | verbose, strict_ports, run or-kimi-k2-2025-verbose-strict_ports | openai | 25.6% | ||
| spec, topology_ports, run lb-gemma2-spec-topology_ports | ollama | 24% | 110 | ||
| spec, topology_ports, run lb-gemma3-spec-topology_ports | ollama | 24% | 194 | ||
| spec, topology_ports, run 20260613-042138-gemma2 | ollama | 22.4% | 111 | ||
| spec, strict_ports, run lb-llama3.1-spec-strict_ports | ollama | 22.4% | 156 | ||
| Kimi K2 Sep 2025 | short, strict_ports, run or-kimi-k2-2025-short-strict_ports | openai | 20.8% | ||
| spec, strict_ports, run lb-gemma2-spec-strict_ports | ollama | 19.2% | 123 | ||
| Kimi K2 Sep 2025 | short, conventions, run or-kimi-k2-2025-short-conventions | openai | 19.2% | ||
| Claude Haiku 4.5 | short, strict_ports, run fe-haiku-short-strict_ports | anthropic | 19.2% | 553 | |
| Claude Haiku 4.5 | short, conventions, run fe-haiku-short-conventions | anthropic | 18.4% | 524 | |
| spec, strict_ports, run 20260613-045341-gemma2 | ollama | 17.6% | 122 | ||
| verbose, strict_ports, run or-llama-4-maverick-2026-verbose-strict_ports | openai | 13.6% | |||
| short, topology_ports, run 20260622-224557-gemma-4-31b | openai | 12.8% | 218 | ||
| short, conventions, run or-llama-4-maverick-2026-short-conventions | openai | 12% | |||
| Claude Sonnet 4.6 | short, topology, run fe-sonnet-short-topology | anthropic | 12% | 848 | |
| short, strict_ports, run or-llama-4-maverick-2026-short-strict_ports | openai | 11.2% | |||
| gpt-oss-20b | verbose, strict_ports, run lb-gptoss-20b-verbose-strict_ports | ollama | 9.60% | 5 | |
| verbose, strict_ports, run or-qwen3-235b-verbose-strict_ports | openai | 8.80% | 217 | ||
| spec, topology_ports, run 20260613-042138-llama3.1 | ollama | 7.20% | 177 | ||
| short, conventions, run or-qwen3-235b-short-conventions | openai | 7.20% | 251 | ||
| short, conventions, run gemma-4-31b-conventions-short | openai | 7.20% | 219 | ||
| spec, conventions, run lb-coder-spec-conventions | ollama | 6.40% | 102 | ||
| verbose, strict_ports, run or-llama-3.3-70b-2025-verbose-strict_ports | openai | 6.40% | |||
| gpt-oss-20b | short, topology_ports, run lb-gptoss-20b-short-topology_ports | ollama | 6.40% | 569 | |
| short, strict_ports, run or-qwen3-235b-short-strict_ports | openai | 5.60% | 240 | ||
| spec, topology_ports, run lb-llama3.1-spec-topology_ports | ollama | 4.80% | 179 | ||
| verbose, conventions, run lb-qwen3-14b-verbose-conventions | ollama | 4.80% | 211 | ||
| gpt-oss-20b | verbose, conventions, run lb-gptoss-20b-verbose-conventions | ollama | 4.80% | 505 | |
| verbose, strict_ports, run lb-coder-verbose-strict_ports | ollama | 4.00% | 346 | ||
| short, conventions, run or-llama-3.3-70b-2025-short-conventions | openai | 4.00% | |||
| gpt-oss-20b | short, conventions, run lb-gptoss-20b-short-conventions | ollama | 4.00% | 539 | |
| spec, topology, run lb-coder-spec-topology | ollama | 3.20% | 104 | ||
| short, conventions, run lb-qwen3-14b-short-conventions | ollama | 3.20% | 205 | ||
| gpt-oss-20b | short, strict_ports, run lb-gptoss-20b-short-strict_ports | ollama | 3.20% | 543 | |
| Claude Haiku 4.5 | short, topology, run fe-haiku-short-topology | anthropic | 3.20% | 404 | |
| short, strict_ports, run lb-coder-short-strict_ports | ollama | 2.40% | 212 | ||
| spec, conventions, run lb-gemma2-spec-conventions | ollama | 1.60% | 141 | ||
| Qwen2.5-Coder-14B | short, strict_ports, run lb-coder14b-short-strict_ports | ollama | 1.60% | 215 | |
| short, topology_ports, run lb-coder-short-topology_ports | ollama | 1.60% | 150 | ||
| short, strict_ports, run or-llama-3.3-70b-2025-short-strict_ports | openai | 1.60% | |||
| short, strict_ports, run lb-qwen3-14b-short-strict_ports | ollama | 1.60% | 233 | ||
| short, strict_ports, run lb-thinkfalse-qwen3-14b-short-strict_ports | ollama | 1.60% | 234 | ||
| GPT-5.5 | short, formatted, run or-gpt-5.5-short-formatted | openai | 1.60% | 2,341 | |
| short, strict_ports, run lb-gemma2-short-strict_ports | ollama | 0.80% | 107 | ||
| verbose, strict_ports, run lb-gemma2-verbose-strict_ports | ollama | 0.80% | 94 | ||
| Qwen2.5-Coder-14B | short, topology_ports, run lb-coder14b-short-topology_ports | ollama | 0.80% | 208 | |
| verbose, conventions, run lb-coder-verbose-conventions | ollama | 0.80% | 802 | ||
| short, strict_ports, run lb-gemma3-short-strict_ports | ollama | 0.80% | 281 | ||
| spec, topology, run lb-gemma3-spec-topology | ollama | 0.80% | 240 | ||
| verbose, strict_ports, run lb-gemma3-verbose-strict_ports | ollama | 0.80% | 289 | ||
| short, topology, run lb-qwen3-14b-short-topology | ollama | 0.80% | 237 | ||
| verbose, strict_ports, run lb-qwen3-14b-verbose-strict_ports | ollama | 0.80% | 248 | ||
| short, conventions, run lb-gemma2-short-conventions | ollama | 0% | 227 | ||
| short, topology, run lb-gemma2-short-topology | ollama | 0% | 146 | ||
| short, topology_ports, run lb-gemma2-short-topology_ports | ollama | 0% | 146 | ||
| spec, topology, run lb-gemma2-spec-topology | ollama | 0% | 138 | ||
| verbose, conventions, run lb-gemma2-verbose-conventions | ollama | 0% | 126 | ||
| short, conventions, run lb-llama3.1-short-conventions | ollama | 0% | 246 | ||
| short, strict_ports, run lb-llama3.1-short-strict_ports | ollama | 0% | 241 | ||
| short, topology, run lb-llama3.1-short-topology | ollama | 0% | 222 | ||
| short, topology_ports, run lb-llama3.1-short-topology_ports | ollama | 0% | 307 | ||
| spec, conventions, run lb-llama3.1-spec-conventions | ollama | 0% | 179 | ||
| spec, topology, run lb-llama3.1-spec-topology | ollama | 0% | 180 | ||
| verbose, conventions, run lb-llama3.1-verbose-conventions | ollama | 0% | 218 | ||
| verbose, strict_ports, run lb-llama3.1-verbose-strict_ports | ollama | 0% | 280 | ||
| Qwen2.5-Coder-14B | short, conventions, run lb-coder14b-short-conventions | ollama | 0% | 272 | |
| Qwen2.5-Coder-14B | short, topology, run lb-coder14b-short-topology | ollama | 0% | 218 | |
| Qwen2.5-Coder-14B | verbose, conventions, run lb-coder14b-verbose-conventions | ollama | 0% | 240 | |
| Qwen2.5-Coder-14B | verbose, strict_ports, run lb-coder14b-verbose-strict_ports | ollama | 0% | 233 | |
| short, conventions, run lb-coder-short-conventions | ollama | 0% | 803 | ||
| short, topology, run lb-coder-short-topology | ollama | 0% | 342 | ||
| short, conventions, run lb-gemma3-short-conventions | ollama | 0% | 276 | ||
| short, topology, run lb-gemma3-short-topology | ollama | 0% | 372 | ||
| short, topology_ports, run lb-gemma3-short-topology_ports | ollama | 0% | 318 | ||
| spec, conventions, run lb-gemma3-spec-conventions | ollama | 0% | 212 | ||
| verbose, conventions, run lb-gemma3-verbose-conventions | ollama | 0% | 261 | ||
| short, topology_ports, run lb-qwen3-14b-short-topology_ports | ollama | 0% | 240 | ||
| gpt-oss-20b | short, topology, run lb-gptoss-20b-short-topology | ollama | 0% | 632 | |
| GLM-5.1 | short, formatted, run or-glm-5.1-short-formatted | openai | 0% | 5,439 | |
| Kimi K2.6 | short, formatted, run or-kimi-k2.6-short-formatted | openai | 0% | 8,574 | |
| short, formatted, run or-deepseek-v4-pro-short-formatted | openai | 0% | 2,303 | ||
| GLM-5.2 | short, formatted, run or-glm-5.2-short-formatted | openai | 0% | 3,857 |
More effort adds a median 40 points
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: Official CircuitRubric leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.8 | spec, conventions, run fe-opus-spec-conventions | anthropic | 96% | 212 | |
| GPT-5.5 | spec, strict_ports, run or-gpt-5.5-closed-spec-strict_ports | openai | 95.2% | ||
| spec, strict_ports, run or-qwen3.7-plus-2026-spec-strict_ports | openai | 95.2% | 55 | ||
| Kimi K2.6 | spec, strict_ports, run or-kimi-k2.6-2026-spec-strict_ports | openai | 94.4% | 163 | |
| Claude Sonnet 4.6 | spec, conventions, run fe-sonnet-spec-conventions | anthropic | 92.8% | 325 | |
| Claude Opus 4.8 | short, conventions, xhigh, run fe-opus48-xhigh-short-conventions | anthropic | 92.8% | 1,777 | |
| spec, strict_ports, run or-deepseek-v4-pro-2026-spec-strict_ports | openai | 92% | 181 | ||
| spec, strict_ports, run or-qwen3.7-max-2026-spec-strict_ports | openai | 92% | |||
| Claude Sonnet 4.6 | spec, strict_ports, run fe-sonnet-spec-strict_ports | anthropic | 91.2% | 302 | |
| GLM-5.1 | spec, strict_ports, run or-glm-5.1-2026-spec-strict_ports | openai | 91.2% | 27 | |
| short, conventions, run 20260623-020043-gemini-3.1-pro | openai | 89.6% | 1,546 | ||
| spec, strict_ports, run or-minimax-m3-2026-spec-strict_ports | openai | 89.6% | 82 | ||
| short, topology_ports, run 20260622-224557-gemini-3.1-pro | openai | 88.8% | 2,024 | ||
| Claude Haiku 4.5 | spec, strict_ports, run fe-haiku-spec-strict_ports | anthropic | 88% | 200 | |
| spec, strict_ports, run or-llama-4-maverick-2026-spec-strict_ports | openai | 85.6% | |||
| GLM-4.5 | spec, strict_ports, run or-glm-4.5-2025-spec-strict_ports | openai | 85.6% | 680 | |
| GPT-5.5 | short, conventions, run or-gpt-5.5-closed-short-conventions | openai | 85.6% | 882 | |
| spec, strict_ports, run or-deepseek-v4-flash-2026-spec-strict_ports | openai | 85.6% | |||
| spec, strict_ports, run or-llama-3.3-70b-2025-spec-strict_ports | openai | 84.8% | |||
| Claude Haiku 4.5 | spec, conventions, run fe-haiku-spec-conventions | anthropic | 84.8% | 239 | |
| short, strict_ports, run 20260623-020041-gemini-3.1-pro | openai | 84.8% | 1,641 | ||
| short, topology_ports, low, run gemini-3.1-pro-low-short-topology_ports | openai | 84.8% | 828 | ||
| GPT-5.5 | verbose, strict_ports, run or-gpt-5.5-closed-verbose-strict_ports | openai | 84.8% | 130 | |
| Claude Opus 4.8 | short, topology_ports, max, run fe-opus48-max-short-topology_ports | anthropic | 84% | 4,289 | |
| Kimi K2 Sep 2025 | spec, strict_ports, run or-kimi-k2-2025-spec-strict_ports | openai | 82.4% | 1 | |
| Claude Opus 4.8 | short, topology_ports, xhigh, run fe-opus48-xhigh-short-topology_ports | anthropic | 82.4% | 114 | |
| verbose, strict_ports, run or-qwen3.7-max-2026-verbose-strict_ports | openai | 79.2% | 3,755 | ||
| gpt-oss-20b | spec, strict_ports, run lb-gptoss-20b-spec-strict_ports | ollama | 78.4% | 240 | |
| GPT-5.5 | short, topology_ports, xhigh, run or-gpt-5.5-xhigh-short-topology_ports | openai | 77.6% | 2,968 | |
| Claude Opus 4.8 | short, strict_ports, xhigh, run fe-opus48-xhigh-short-strict_ports | anthropic | 77.6% | 1,788 | |
| gpt-oss-20b | spec, topology_ports, run lb-gptoss-20b-spec-topology_ports | ollama | 75.2% | 268 | |
| Kimi K2.6 | verbose, strict_ports, run or-kimi-k2.6-2026-verbose-strict_ports | openai | 75.2% | 3,255 | |
| GPT-5.5 | short, topology_ports, run or-gpt-5.5-short-topology_ports | openai | 75.2% | 1,044 | |
| Claude Opus 4.8 | short, topology_ports, high, run fe-opus48-high-short-topology_ports | anthropic | 75.2% | 896 | |
| Claude Opus 4.8 | verbose, conventions, run fe-opus-verbose-conventions | anthropic | 75.2% | 308 | |
| Claude Opus 4.8 | verbose, strict_ports, run fe-opus-verbose-strict_ports | anthropic | 75.2% | 301 | |
| GLM-5.1 | verbose, strict_ports, run or-glm-5.1-2026-verbose-strict_ports | openai | 72% | 545 | |
| GPT-5.5 | short, strict_ports, run or-gpt-5.5-closed-short-strict_ports | openai | 72% | 981 | |
| Claude Opus 4.7 | short, topology_ports, high, run fe-opus47-high-short-topology_ports | anthropic | 71.2% | 1,065 | |
| Claude Opus 4.8 | short, conventions, run fe-opus-short-conventions | anthropic | 68.8% | 303 | |
| Claude Opus 4.7 | short, conventions, run fe-opus47-short-conventions | anthropic | 68% | 277 | |
| Kimi K2.6 | short, conventions, run or-kimi-k2.6-2026-short-conventions | openai | 68% | 1,966 | |
| spec, topology_ports, run 20260613-042138-qwen2.5-coder | ollama | 66.4% | 114 | ||
| Kimi K2.6 | short, strict_ports, run or-kimi-k2.6-2026-short-strict_ports | openai | 66.4% | 774 | |
| Claude Sonnet 4.6 | verbose, conventions, run fe-sonnet-verbose-conventions | anthropic | 65.6% | 587 | |
| Claude Opus 4.7 | short, strict_ports, run fe-opus47-short-strict_ports | anthropic | 65.6% | 294 | |
| short, strict_ports, run or-qwen3.7-max-2026-short-strict_ports | openai | 65.6% | 3,546 | ||
| spec, topology_ports, run lb-coder-spec-topology_ports | ollama | 64.8% | 115 | ||
| Claude Sonnet 4.6 | verbose, strict_ports, run fe-sonnet-verbose-strict_ports | anthropic | 64.8% | 589 | |
| GLM-5.1 | short, conventions, run or-glm-5.1-2026-short-conventions | openai | 64% | 512 | |
| spec, strict_ports, run 20260613-045341-qwen2.5-coder | ollama | 63.2% | 111 | ||
| GLM-5.1 | short, topology_ports, run or-glm-5.1-short-topology_ports | openai | 63.2% | 3,958 | |
| GLM-5.1 | short, strict_ports, run or-glm-5.1-2026-short-strict_ports | openai | 62.4% | 1,421 | |
| short, conventions, run or-qwen3.7-max-2026-short-conventions | openai | 62.4% | 3,840 | ||
| Claude Opus 4.8 | short, topology_ports, xhigh, run fe-opus48-xhigh-nothink-short-topology_ports | anthropic | 62.4% | 25 | |
| spec, strict_ports, run lb-coder-spec-strict_ports | ollama | 61.6% | 112 | ||
| Claude Opus 4.7 | short, topology_ports, run fe-opus47-short-topology_ports | anthropic | 61.6% | 344 | |
| verbose, strict_ports, run or-qwen3.7-plus-2026-verbose-strict_ports | openai | 61.6% | 5,455 | ||
| spec, strict_ports, run or-qwen3-235b-spec-strict_ports | openai | 59.2% | 151 | ||
| Claude Opus 4.8 | short, strict_ports, run fe-opus-short-strict_ports | anthropic | 59.2% | 270 | |
| verbose, strict_ports, run or-deepseek-v4-pro-2026-verbose-strict_ports | openai | 58.4% | 671 | ||
| short, topology_ports, run 20260622-224557-gemini-3.5-flash | openai | 58.4% | 2,494 | ||
| Kimi K2.6 | short, topology_ports, run or-kimi-k2.6-short-topology_ports | openai | 57.6% | 7,603 | |
| verbose, strict_ports, run or-minimax-m3-2026-verbose-strict_ports | openai | 55.2% | 2,183 | ||
| spec, topology, run lb-qwen3-14b-spec-topology | ollama | 54.4% | 178 | ||
| Claude Opus 4.8 | short, topology_ports, run fe-opus48-short-topology_ports | anthropic | 53.6% | 338 | |
| spec, strict_ports, run lb-qwen3-14b-spec-strict_ports | ollama | 52% | 135 | ||
| short, conventions, run or-deepseek-v4-pro-2026-short-conventions | openai | 52% | 452 | ||
| short, strict_ports, run or-deepseek-v4-pro-2026-short-strict_ports | openai | 52% | 731 | ||
| short, topology_ports, run or-qwen3.7-max-short-topology_ports | openai | 52% | 4,934 | ||
| short, conventions, run or-qwen3.7-plus-2026-short-conventions | openai | 52% | 4,854 | ||
| spec, conventions, run lb-qwen3-14b-spec-conventions | ollama | 48.8% | 166 | ||
| short, strict_ports, run or-qwen3.7-plus-2026-short-strict_ports | openai | 48.8% | 4,755 | ||
| GLM-4.5 | verbose, strict_ports, run or-glm-4.5-2025-verbose-strict_ports | openai | 48% | 4,761 | |
| Claude Sonnet 4.6 | short, strict_ports, run fe-sonnet-short-strict_ports | anthropic | 48% | 599 | |
| short, conventions, run or-minimax-m3-2026-short-conventions | openai | 45.6% | 2,476 | ||
| short, strict_ports, run or-minimax-m3-2026-short-strict_ports | openai | 45.6% | 1,648 | ||
| GLM-5.2 | short, topology_ports, run or-glm-5.2-short-topology_ports | openai | 44.8% | 4,045 | |
| Claude Sonnet 4.6 | short, conventions, run fe-sonnet-short-conventions | anthropic | 44% | 594 | |
| Qwen2.5-Coder-14B | spec, strict_ports, run lb-coder14b-spec-strict_ports | ollama | 42.4% | 166 | |
| gpt-oss-20b | spec, topology, run lb-gptoss-20b-spec-topology | ollama | 41.6% | 270 | |
| verbose, strict_ports, run or-deepseek-v4-flash-2026-verbose-strict_ports | openai | 41.6% | |||
| Qwen2.5-Coder-14B | spec, conventions, run lb-coder14b-spec-conventions | ollama | 40% | 168 | |
| short, topology_ports, run or-deepseek-v4-pro-short-topology_ports | openai | 40% | 2,045 | ||
| spec, strict_ports, run lb-gemma3-spec-strict_ports | ollama | 34.4% | 222 | ||
| GLM-4.5 | short, strict_ports, run or-glm-4.5-2025-short-strict_ports | openai | 33.6% | 5,574 | |
| short, strict_ports, run or-deepseek-v4-flash-2026-short-strict_ports | openai | 33.6% | 863 | ||
| short, conventions, run or-deepseek-v4-flash-2026-short-conventions | openai | 32.8% | 1,320 | ||
| Qwen2.5-Coder-14B | spec, topology, run lb-coder14b-spec-topology | ollama | 32% | 196 | |
| gpt-oss-20b | spec, conventions, run lb-gptoss-20b-spec-conventions | ollama | 32% | 258 | |
| Qwen2.5-Coder-14B | spec, topology_ports, run lb-coder14b-spec-topology_ports | ollama | 30.4% | 99 | |
| spec, topology_ports, run lb-qwen3-14b-spec-topology_ports | ollama | 30.4% | 122 | ||
| Claude Haiku 4.5 | verbose, strict_ports, run fe-haiku-verbose-strict_ports | anthropic | 30.4% | 540 | |
| spec, strict_ports, run 20260613-045341-llama3.1 | ollama | 27.2% | 159 | ||
| GLM-4.5 | short, conventions, run or-glm-4.5-2025-short-conventions | openai | 26.4% | 6,048 | |
| Claude Haiku 4.5 | verbose, conventions, run fe-haiku-verbose-conventions | anthropic | 26.4% | 552 | |
| Kimi K2 Sep 2025 | verbose, strict_ports, run or-kimi-k2-2025-verbose-strict_ports | openai | 25.6% | ||
| spec, topology_ports, run lb-gemma2-spec-topology_ports | ollama | 24% | 110 | ||
| spec, topology_ports, run lb-gemma3-spec-topology_ports | ollama | 24% | 194 | ||
| spec, topology_ports, run 20260613-042138-gemma2 | ollama | 22.4% | 111 | ||
| spec, strict_ports, run lb-llama3.1-spec-strict_ports | ollama | 22.4% | 156 | ||
| Kimi K2 Sep 2025 | short, strict_ports, run or-kimi-k2-2025-short-strict_ports | openai | 20.8% | ||
| spec, strict_ports, run lb-gemma2-spec-strict_ports | ollama | 19.2% | 123 | ||
| Kimi K2 Sep 2025 | short, conventions, run or-kimi-k2-2025-short-conventions | openai | 19.2% | ||
| Claude Haiku 4.5 | short, strict_ports, run fe-haiku-short-strict_ports | anthropic | 19.2% | 553 | |
| Claude Haiku 4.5 | short, conventions, run fe-haiku-short-conventions | anthropic | 18.4% | 524 | |
| spec, strict_ports, run 20260613-045341-gemma2 | ollama | 17.6% | 122 | ||
| verbose, strict_ports, run or-llama-4-maverick-2026-verbose-strict_ports | openai | 13.6% | |||
| short, topology_ports, run 20260622-224557-gemma-4-31b | openai | 12.8% | 218 | ||
| short, conventions, run or-llama-4-maverick-2026-short-conventions | openai | 12% | |||
| Claude Sonnet 4.6 | short, topology, run fe-sonnet-short-topology | anthropic | 12% | 848 | |
| short, strict_ports, run or-llama-4-maverick-2026-short-strict_ports | openai | 11.2% | |||
| gpt-oss-20b | verbose, strict_ports, run lb-gptoss-20b-verbose-strict_ports | ollama | 9.60% | 5 | |
| verbose, strict_ports, run or-qwen3-235b-verbose-strict_ports | openai | 8.80% | 217 | ||
| spec, topology_ports, run 20260613-042138-llama3.1 | ollama | 7.20% | 177 | ||
| short, conventions, run or-qwen3-235b-short-conventions | openai | 7.20% | 251 | ||
| short, conventions, run gemma-4-31b-conventions-short | openai | 7.20% | 219 | ||
| spec, conventions, run lb-coder-spec-conventions | ollama | 6.40% | 102 | ||
| verbose, strict_ports, run or-llama-3.3-70b-2025-verbose-strict_ports | openai | 6.40% | |||
| gpt-oss-20b | short, topology_ports, run lb-gptoss-20b-short-topology_ports | ollama | 6.40% | 569 | |
| short, strict_ports, run or-qwen3-235b-short-strict_ports | openai | 5.60% | 240 | ||
| spec, topology_ports, run lb-llama3.1-spec-topology_ports | ollama | 4.80% | 179 | ||
| verbose, conventions, run lb-qwen3-14b-verbose-conventions | ollama | 4.80% | 211 | ||
| gpt-oss-20b | verbose, conventions, run lb-gptoss-20b-verbose-conventions | ollama | 4.80% | 505 | |
| verbose, strict_ports, run lb-coder-verbose-strict_ports | ollama | 4.00% | 346 | ||
| short, conventions, run or-llama-3.3-70b-2025-short-conventions | openai | 4.00% | |||
| gpt-oss-20b | short, conventions, run lb-gptoss-20b-short-conventions | ollama | 4.00% | 539 | |
| spec, topology, run lb-coder-spec-topology | ollama | 3.20% | 104 | ||
| short, conventions, run lb-qwen3-14b-short-conventions | ollama | 3.20% | 205 | ||
| gpt-oss-20b | short, strict_ports, run lb-gptoss-20b-short-strict_ports | ollama | 3.20% | 543 | |
| Claude Haiku 4.5 | short, topology, run fe-haiku-short-topology | anthropic | 3.20% | 404 | |
| short, strict_ports, run lb-coder-short-strict_ports | ollama | 2.40% | 212 | ||
| spec, conventions, run lb-gemma2-spec-conventions | ollama | 1.60% | 141 | ||
| Qwen2.5-Coder-14B | short, strict_ports, run lb-coder14b-short-strict_ports | ollama | 1.60% | 215 | |
| short, topology_ports, run lb-coder-short-topology_ports | ollama | 1.60% | 150 | ||
| short, strict_ports, run or-llama-3.3-70b-2025-short-strict_ports | openai | 1.60% | |||
| short, strict_ports, run lb-qwen3-14b-short-strict_ports | ollama | 1.60% | 233 | ||
| short, strict_ports, run lb-thinkfalse-qwen3-14b-short-strict_ports | ollama | 1.60% | 234 | ||
| GPT-5.5 | short, formatted, run or-gpt-5.5-short-formatted | openai | 1.60% | 2,341 | |
| short, strict_ports, run lb-gemma2-short-strict_ports | ollama | 0.80% | 107 | ||
| verbose, strict_ports, run lb-gemma2-verbose-strict_ports | ollama | 0.80% | 94 | ||
| Qwen2.5-Coder-14B | short, topology_ports, run lb-coder14b-short-topology_ports | ollama | 0.80% | 208 | |
| verbose, conventions, run lb-coder-verbose-conventions | ollama | 0.80% | 802 | ||
| short, strict_ports, run lb-gemma3-short-strict_ports | ollama | 0.80% | 281 | ||
| spec, topology, run lb-gemma3-spec-topology | ollama | 0.80% | 240 | ||
| verbose, strict_ports, run lb-gemma3-verbose-strict_ports | ollama | 0.80% | 289 | ||
| short, topology, run lb-qwen3-14b-short-topology | ollama | 0.80% | 237 | ||
| verbose, strict_ports, run lb-qwen3-14b-verbose-strict_ports | ollama | 0.80% | 248 | ||
| short, conventions, run lb-gemma2-short-conventions | ollama | 0% | 227 | ||
| short, topology, run lb-gemma2-short-topology | ollama | 0% | 146 | ||
| short, topology_ports, run lb-gemma2-short-topology_ports | ollama | 0% | 146 | ||
| spec, topology, run lb-gemma2-spec-topology | ollama | 0% | 138 | ||
| verbose, conventions, run lb-gemma2-verbose-conventions | ollama | 0% | 126 | ||
| short, conventions, run lb-llama3.1-short-conventions | ollama | 0% | 246 | ||
| short, strict_ports, run lb-llama3.1-short-strict_ports | ollama | 0% | 241 | ||
| short, topology, run lb-llama3.1-short-topology | ollama | 0% | 222 | ||
| short, topology_ports, run lb-llama3.1-short-topology_ports | ollama | 0% | 307 | ||
| spec, conventions, run lb-llama3.1-spec-conventions | ollama | 0% | 179 | ||
| spec, topology, run lb-llama3.1-spec-topology | ollama | 0% | 180 | ||
| verbose, conventions, run lb-llama3.1-verbose-conventions | ollama | 0% | 218 | ||
| verbose, strict_ports, run lb-llama3.1-verbose-strict_ports | ollama | 0% | 280 | ||
| Qwen2.5-Coder-14B | short, conventions, run lb-coder14b-short-conventions | ollama | 0% | 272 | |
| Qwen2.5-Coder-14B | short, topology, run lb-coder14b-short-topology | ollama | 0% | 218 | |
| Qwen2.5-Coder-14B | verbose, conventions, run lb-coder14b-verbose-conventions | ollama | 0% | 240 | |
| Qwen2.5-Coder-14B | verbose, strict_ports, run lb-coder14b-verbose-strict_ports | ollama | 0% | 233 | |
| short, conventions, run lb-coder-short-conventions | ollama | 0% | 803 | ||
| short, topology, run lb-coder-short-topology | ollama | 0% | 342 | ||
| short, conventions, run lb-gemma3-short-conventions | ollama | 0% | 276 | ||
| short, topology, run lb-gemma3-short-topology | ollama | 0% | 372 | ||
| short, topology_ports, run lb-gemma3-short-topology_ports | ollama | 0% | 318 | ||
| spec, conventions, run lb-gemma3-spec-conventions | ollama | 0% | 212 | ||
| verbose, conventions, run lb-gemma3-verbose-conventions | ollama | 0% | 261 | ||
| short, topology_ports, run lb-qwen3-14b-short-topology_ports | ollama | 0% | 240 | ||
| gpt-oss-20b | short, topology, run lb-gptoss-20b-short-topology | ollama | 0% | 632 | |
| GLM-5.1 | short, formatted, run or-glm-5.1-short-formatted | openai | 0% | 5,439 | |
| Kimi K2.6 | short, formatted, run or-kimi-k2.6-short-formatted | openai | 0% | 8,574 | |
| short, formatted, run or-deepseek-v4-pro-short-formatted | openai | 0% | 2,303 | ||
| GLM-5.2 | short, formatted, run or-glm-5.2-short-formatted | openai | 0% | 3,857 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official CircuitRubric leaderboard
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 CircuitRubric 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%
- AnalogCoder Not in model cards Models write Python programs that build analog circuits. A simulator checks whether each circuit performs its requested function. The authors report first-attempt success and how many tasks each model solves.
Llama 3.1-405B 83.3%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (35 entries).
- Pass Models scored 28 models we track, plus 7 other entries on its leaderboard.
- Pass Newest score The newest is from June 2026, for GLM-5.2.
- 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 96%, past 85% since April 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 178 rows for models we track and 7 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.