Razavi-Bench
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.
The authors rank 73 models on 50 questions. Each model answers every question three times without tools.
- Made by
- Zhishuai Zhang, Oscar Toomey, and Taekwang Jang
- Kind
- Electronics
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Carbon leads with 98.3% Gemini 4 Carbon leads with 98.3%
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.
- 98.3
Gemini 4 Carbon
- 97.7 Claude Opus 5.5
- 95.8 Claude Fable 5.2
- 94.8
Gemini 4 Argon
- 94.7 GPT-6 Astra
- 94.0 Claude Opus 5
- 93.7 Claude Fable 5.1
- 92.8 GPT-6.1 Sol
- 90.5 Claude Fable 5
- 90.3
Tencent Hy4
- 89.7 GPT-5.6 Sol
- 88.7
Gemini 3.8 Flash
- 88.5
Gemini 3.7 Flash
- 87.8 Muse Wonder Full 1.0
- 87.8 GPT-6 Sol
- 86.7 GPT-5.6 Terra
- 86.5 GPT-5.5
- 85.5
Gemini 3.5 Flash
- 84.8 Kimi 3.1 Pro
- 84.0
Gemini 3.6 Flash
- 83.7
Muse Spark 1.2
- 83.0 GPT-5.4
- 82.7 Claude Opus 4.8
- 82.3 GPT-5.3
- 81.3
Qwen 3.8 Max
- 80.5
Muse Spark 1.3
- 80.2 Claude Haiku 5.5
- 79.8 GLM-5.3-Flash
- 79.3
Gemini 3 Flash
- 77.7
Gemini 3.1 Pro
- 77.3
DeepSeek V4.1 Flash 1017
- 77.0 GPT-5.6 Luna
- 75.8 Grok 4.6
- 75.5 GPT-6 Luna
- 74.5 Grok 4.5
- 73.7 GPT-5.2
- 73.5 Kimi K3
- 72.7
MiniMax-M3.1-Flash
- 71.8
Qwen3.7-Plus
- 71.2 Grok 4.7
- 70.3
Mistral Large 4
- 69.7 DeepSeek V4.1 Flash 0910
- 69.2
MiniMax-M3
- 67.0
Qwen 3.8 27B
- 66.8 GPT-5.4 Mini
- 65.0
Qwen3.7 Flash
- 64.2 Kimi K2.7 Code
- 62.2 Claude Sonnet 4.6
- 58.5
Inkling-Small
- 56.8
Gemini 2.5 Pro
- 55.0 GPT-5.1
- 54.8 Mimo 2.6 Pro
- 53.3 GPT-5
- 52.8 Claude Opus 4.5
- 51.5 o3
- 51.5
Gemma 4 31B IT
- 48.7
Inkling
- 47.5
Step 3.7 Flash
- 46.0
Llama 4 Maverick
- 44.2 Claude Sonnet 4.5
- 43.2
Qwen3.5-9B
- 42.5
Gemini 2.5 Flash-Lite
- 37.5
Nemotron 3.5 Super VL
- 36.5
Mistral Medium 3.5
- 36.0
Qwen3-VL-235B-A22B-Instruct
- 31.7 GPT-4o (2024-11-20)
- 31.2 GPT-4o (2024-08-06)
- 31.2 Claude Haiku 4.5
- 28.8 GPT-4o (2024-05-13)
- 28.0 Mistral Large 2512
- 26.3
Qwen2.5-VL-72B
- 25.7 GPT-4o mini
- 21.7 Nova Pro
- 1
Gemini 4 Carbon high 98.3%
- 2 Claude Opus 5.5 max 97.7%
- 3 Claude Fable 5.2 max 95.8%
- 4
Gemini 4 Argon high 94.8%
- 5 GPT-6 Astra max 94.7%
- 6 Claude Opus 5 max 94%
- 7 Claude Fable 5.1 max 93.7%
- 8 GPT-6.1 Sol max 92.8%
- 9 Claude Fable 5 max 90.5%
- 10
Tencent Hy4 high 90.3%
- 11 GPT-5.6 Sol max 89.7%
- 12
Gemini 3.8 Flash high 88.7%
- 13
Gemini 3.7 Flash high 88.5%
- 14 Muse Wonder Full 1.0 max 87.8%
- 15 GPT-6 Sol max 87.8%
- 16 GPT-5.6 Terra max 86.7%
- 17 GPT-5.5 xhigh 86.5%
- 18
Gemini 3.5 Flash high 85.5%
- 19 Kimi 3.1 Pro max 84.8%
- 20
Gemini 3.6 Flash high 84%
- 21
Muse Spark 1.2 xhigh 83.7%
- 22 GPT-5.4 xhigh 83%
- 23 Claude Opus 4.8 max 82.7%
- 24 GPT-5.3 xhigh 82.3%
- 25
Qwen 3.8 Max xhigh 81.3%
- 26
Muse Spark 1.3 max 80.5%
- 27 Claude Haiku 5.5 max 80.2%
- 28 GLM-5.3-Flash max 79.8%
- 29
Gemini 3 Flash high 79.3%
- 30
Gemini 3.1 Pro high 77.7%
- 31
DeepSeek V4.1 Flash 1017 max 77.3%
- 32 GPT-5.6 Luna max 77%
- 33 Grok 4.6 xhigh 75.8%
- 34 GPT-6 Luna max 75.5%
- 35 Grok 4.5 high 74.5%
- 36 GPT-5.2 xhigh 73.7%
- 37 Kimi K3 max 73.5%
- 38
MiniMax-M3.1-Flash max 72.7%
- 39
Qwen3.7-Plus max 71.8%
- 40 Grok 4.7 xhigh 71.2%
- 41
Mistral Large 4 high 70.3%
- 42 DeepSeek V4.1 Flash 0910 max 69.7%
- 43
MiniMax-M3 thinking 69.2%
- 44
Qwen 3.8 27B xhigh 67%
- 45 GPT-5.4 Mini xhigh 66.8%
- 46
Qwen3.7 Flash max 65%
- 47 Kimi K2.7 Code thinking 64.2%
- 48 Claude Sonnet 4.6 max 62.2%
- 49
Inkling-Small max 58.5%
- 50
Gemini 2.5 Pro Jun 2025, max 56.8%
- 51 GPT-5.1 high 55%
- 52 Mimo 2.6 Pro max 54.8%
- 53 GPT-5 high 53.3%
- 54 Claude Opus 4.5 max 52.8%
- 55 o3 high 51.5%
- 56
Gemma 4 31B IT max 51.5%
- 57
Inkling max 48.7%
- 58
Step 3.7 Flash high 47.5%
- 59
Llama 4 Maverick default 46%
- 60 Claude Sonnet 4.5 max 44.2%
- 61
Qwen3.5-9B thinking 43.2%
- 62
Gemini 2.5 Flash-Lite Sep 2025, max 42.5%
- 63
Nemotron 3.5 Super VL max 37.5%
- 64
Mistral Medium 3.5 high 36.5%
- 65
Qwen3-VL-235B-A22B-Instruct default 36%
- 66 GPT-4o (2024-11-20) default 31.7%
- 67 GPT-4o (2024-08-06) default 31.2%
- 68 Claude Haiku 4.5 max 31.2%
- 69 GPT-4o (2024-05-13) default 28.8%
- 70 Mistral Large 2512 default 28%
- 71
Qwen2.5-VL-72B default 26.3%
- 72 GPT-4o mini default 25.7%
- 73 Nova Pro default 21.7%
Source: Official Razavi-Bench leaderboard
- 98.3
Gemini 4 Carbon
- 97.7 Claude Opus 5.5
- 95.8 Claude Fable 5.2
- 94.8
Gemini 4 Argon
- 94.7 GPT-6 Astra
- 94.0 Claude Opus 5
- 93.7 Claude Fable 5.1
- 92.8 GPT-6.1 Sol
- 90.5 Claude Fable 5
- 90.3
Tencent Hy4
- 89.7 GPT-5.6 Sol
- 88.7
Gemini 3.8 Flash
- 88.5
Gemini 3.7 Flash
- 87.8 GPT-6 Sol
- 86.7 GPT-5.6 Terra
- 86.5 GPT-5.5
- 85.5
Gemini 3.5 Flash
- 84.0
Gemini 3.6 Flash
- 83.7
Muse Spark 1.2
- 83.0 GPT-5.4
- 82.7 Claude Opus 4.8
- 81.3
Qwen 3.8 Max
- 80.5
Muse Spark 1.3
- 80.2 Claude Haiku 5.5
- 79.8 GLM-5.3-Flash
- 79.3
Gemini 3 Flash
- 77.7
Gemini 3.1 Pro
- 77.3
DeepSeek V4.1 Flash 1017
- 77.0 GPT-5.6 Luna
- 75.8 Grok 4.6
- 75.5 GPT-6 Luna
- 74.5 Grok 4.5
- 73.7 GPT-5.2
- 73.5 Kimi K3
- 72.7
MiniMax-M3.1-Flash
- 71.8
Qwen3.7-Plus
- 71.2 Grok 4.7
- 70.3
Mistral Large 4
- 69.2
MiniMax-M3
- 67.0
Qwen 3.8 27B
- 66.8 GPT-5.4 Mini
- 65.0
Qwen3.7 Flash
- 64.2 Kimi K2.7 Code
- 62.2 Claude Sonnet 4.6
- 58.5
Inkling-Small
- 56.8
Gemini 2.5 Pro
- 55.0 GPT-5.1
- 53.3 GPT-5
- 52.8 Claude Opus 4.5
- 51.5 o3
- 51.5
Gemma 4 31B IT
- 48.7
Inkling
- 47.5
Step 3.7 Flash
- 46.0
Llama 4 Maverick
- 44.2 Claude Sonnet 4.5
- 43.2
Qwen3.5-9B
- 42.5
Gemini 2.5 Flash-Lite
- 37.5
Nemotron 3.5 Super VL
- 36.5
Mistral Medium 3.5
- 36.0
Qwen3-VL-235B-A22B-Instruct
- 31.2 Claude Haiku 4.5
- 26.3
Qwen2.5-VL-72B
- 25.7 GPT-4o mini
- 1
Gemini 4 Carbon high 98.3%
- 2 Claude Opus 5.5 max 97.7%
- 3 Claude Fable 5.2 max 95.8%
- 4
Gemini 4 Argon high 94.8%
- 5 GPT-6 Astra max 94.7%
- 6 Claude Opus 5 max 94%
- 7 Claude Fable 5.1 max 93.7%
- 8 GPT-6.1 Sol max 92.8%
- 9 Claude Fable 5 max 90.5%
- 10
Tencent Hy4 high 90.3%
- 11 GPT-5.6 Sol max 89.7%
- 12
Gemini 3.8 Flash high 88.7%
- 13
Gemini 3.7 Flash high 88.5%
- 14 GPT-6 Sol max 87.8%
- 15 GPT-5.6 Terra max 86.7%
- 16 GPT-5.5 xhigh 86.5%
- 17
Gemini 3.5 Flash high 85.5%
- 18
Gemini 3.6 Flash high 84%
- 19
Muse Spark 1.2 xhigh 83.7%
- 20 GPT-5.4 xhigh 83%
- 21 Claude Opus 4.8 max 82.7%
- 22
Qwen 3.8 Max xhigh 81.3%
- 23
Muse Spark 1.3 max 80.5%
- 24 Claude Haiku 5.5 max 80.2%
- 25 GLM-5.3-Flash max 79.8%
- 26
Gemini 3 Flash high 79.3%
- 27
Gemini 3.1 Pro high 77.7%
- 28
DeepSeek V4.1 Flash 1017 max 77.3%
- 29 GPT-5.6 Luna max 77%
- 30 Grok 4.6 xhigh 75.8%
- 31 GPT-6 Luna max 75.5%
- 32 Grok 4.5 high 74.5%
- 33 GPT-5.2 xhigh 73.7%
- 34 Kimi K3 max 73.5%
- 35
MiniMax-M3.1-Flash max 72.7%
- 36
Qwen3.7-Plus max 71.8%
- 37 Grok 4.7 xhigh 71.2%
- 38
Mistral Large 4 high 70.3%
- 39
MiniMax-M3 thinking 69.2%
- 40
Qwen 3.8 27B xhigh 67%
- 41 GPT-5.4 Mini xhigh 66.8%
- 42
Qwen3.7 Flash max 65%
- 43 Kimi K2.7 Code thinking 64.2%
- 44 Claude Sonnet 4.6 max 62.2%
- 45
Inkling-Small max 58.5%
- 46
Gemini 2.5 Pro Jun 2025, max 56.8%
- 47 GPT-5.1 high 55%
- 48 GPT-5 high 53.3%
- 49 Claude Opus 4.5 max 52.8%
- 50 o3 high 51.5%
- 51
Gemma 4 31B IT max 51.5%
- 52
Inkling max 48.7%
- 53
Step 3.7 Flash high 47.5%
- 54
Llama 4 Maverick default 46%
- 55 Claude Sonnet 4.5 max 44.2%
- 56
Qwen3.5-9B thinking 43.2%
- 57
Gemini 2.5 Flash-Lite Sep 2025, max 42.5%
- 58
Nemotron 3.5 Super VL max 37.5%
- 59
Mistral Medium 3.5 high 36.5%
- 60
Qwen3-VL-235B-A22B-Instruct default 36%
- 61 Claude Haiku 4.5 max 31.2%
- 62
Qwen2.5-VL-72B default 26.3%
- 63 GPT-4o mini default 25.7%
Source: Official Razavi-Bench leaderboard
| # | Entry | Score ± | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 98.3% 98 to 98.5 | high | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 2 | Claude Opus 5.5 | 97.7% 97 to 98.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 3 | Claude Fable 5.2 | 95.8% 95 to 96.5 | max | Nov 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 4 | | 94.8% 93.5 to 95.5 | high | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 5 | GPT-6 Astra | 94.7% 94 to 95.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 6 | Claude Opus 5 | 94% 92.5 to 95 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 7 | Claude Fable 5.1 | 93.7% 92.5 to 95 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 8 | GPT-6.1 Sol | 92.8% 91 to 95 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 9 | Claude Fable 5 | 90.5% ±0.5 | max | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 10 | | 90.3% 88 to 91.5 | high | Nov 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 11 | GPT-5.6 Sol | 89.7% 88.5 to 90.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 12 | | 88.7% 88.5 to 89 | high | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 13 | | 88.5% ±1 | high | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 14 | Muse Wonder Full 1.0 | 87.8% 84.5 to 90.5 | max | razavi-bench.tokenzhang.com | Official leaderboard | |
| 15 | GPT-6 Sol | 87.8% 86 to 89 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 16 | GPT-5.6 Terra | 86.7% 85.5 to 87.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 17 | GPT-5.5 | 86.5% 85 to 87.5 | xhigh | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 18 | | 85.5% 84.5 to 87 | high | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 19 | Kimi 3.1 Pro | 84.8% 84.5 to 85 | max | razavi-bench.tokenzhang.com | Official leaderboard | |
| 20 | | 84% ±0.5 | high | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 21 | | 83.7% 81.5 to 85 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 22 | GPT-5.4 | 83% ±0.5 | xhigh | Mar 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 23 | Claude Opus 4.8 | 82.7% 77 to 85.5 | max | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 24 | GPT-5.3 | 82.3% 81.5 to 83 | xhigh | razavi-bench.tokenzhang.com | Official leaderboard | |
| 25 | | 81.3% 80.5 to 82 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 26 | | 80.5% 79 to 81.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 27 | Claude Haiku 5.5 | 80.2% 79.5 to 80.5 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 28 | GLM-5.3-Flash | 79.8% 79.5 to 80 | max | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 29 | | 79.3% 76.5 to 81.5 | high | Dec 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 30 | | 77.7% 76.5 to 78.5 | high | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 31 | | 77.3% ±4.3 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 32 | GPT-5.6 Luna | 77% 75 to 78.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 33 | Grok 4.6 | 75.8% 74 to 78.5 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 34 | GPT-6 Luna | 75.5% 75 to 76.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 35 | Grok 4.5 | 74.5% ±1.5 | high | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 36 | GPT-5.2 | 73.7% 71.5 to 75 | xhigh | Dec 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 37 | Kimi K3 | 73.5% 70.5 to 76 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 38 | | 72.7% 70 to 78 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 39 | | 71.8% 69 to 74 | max | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 40 | Grok 4.7 | 71.2% 70 to 72 | xhigh | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 41 | | 70.3% 68.5 to 71.5 | high | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 42 | DeepSeek V4.1 Flash 0910 | 69.7% 68.5 to 71 | max | razavi-bench.tokenzhang.com | Official leaderboard | |
| 43 | | 69.2% 68 to 70.5 | thinking | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 44 | | 67% 64.5 to 68.5 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 45 | GPT-5.4 Mini | 66.8% 64.5 to 69.5 | xhigh | Mar 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 46 | | 65% 63.5 to 66 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 47 | Kimi K2.7 Code | 64.2% 60.5 to 66.5 | thinking | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 48 | Claude Sonnet 4.6 | 62.2% 61.5 to 63 | max | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 49 | | 58.5% 56.5 to 62 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 50 | | 56.8% 56 to 57.5 | max | Jun 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 51 | GPT-5.1 | 55% 52.5 to 59.5 | high | Nov 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 52 | Mimo 2.6 Pro | 54.8% 53 to 57 | max | razavi-bench.tokenzhang.com | Official leaderboard | |
| 53 | GPT-5 | 53.3% 51.5 to 55 | high | Aug 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 54 | Claude Opus 4.5 | 52.8% 50 to 54.5 | max | Nov 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 55 | o3 | 51.5% ±1.5 | high | Apr 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 56 | | 51.5% 47 to 55 | max | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 57 | | 48.7% 42.5 to 54 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 58 | | 47.5% 45 to 50.5 | high | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 59 | | 46% 44.5 to 48.5 | default | Apr 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 60 | Claude Sonnet 4.5 | 44.2% 42.5 to 46.5 | max | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 61 | | 43.2% 42 to 44 | thinking | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 62 | | 42.5% | max | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 63 | | 37.5% 35 to 39.5 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 64 | | 36.5% 33.5 to 40 | high | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 65 | | 36% 33 to 38 | default | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 66 | GPT-4o (2024-11-20) | 31.7% 30.5 to 32.5 | default | razavi-bench.tokenzhang.com | Official leaderboard | |
| 67 | GPT-4o (2024-08-06) | 31.2% 30 to 32 | default | razavi-bench.tokenzhang.com | Official leaderboard | |
| 68 | Claude Haiku 4.5 | 31.2% 27.5 to 33.5 | max | Oct 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 69 | GPT-4o (2024-05-13) | 28.8% 28.5 to 29.5 | default | razavi-bench.tokenzhang.com | Official leaderboard | |
| 70 | Mistral Large 2512 | 28% ±1 | default | razavi-bench.tokenzhang.com | Official leaderboard | |
| 71 | | 26.3% 25 to 27 | default | Jan 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 72 | GPT-4o mini | 25.7% 24.5 to 27 | default | Jul 2024 | razavi-bench.tokenzhang.com | Official leaderboard |
| 73 | Nova Pro | 21.7% 20.5 to 23 | default | razavi-bench.tokenzhang.com | Official leaderboard |
| # | Model | Score ± | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 98.3% 98 to 98.5 | high | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 2 | Claude Opus 5.5 | 97.7% 97 to 98.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 3 | Claude Fable 5.2 | 95.8% 95 to 96.5 | max | Nov 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 4 | | 94.8% 93.5 to 95.5 | high | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 5 | GPT-6 Astra | 94.7% 94 to 95.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 6 | Claude Opus 5 | 94% 92.5 to 95 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 7 | Claude Fable 5.1 | 93.7% 92.5 to 95 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 8 | GPT-6.1 Sol | 92.8% 91 to 95 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 9 | Claude Fable 5 | 90.5% ±0.5 | max | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 10 | | 90.3% 88 to 91.5 | high | Nov 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 11 | GPT-5.6 Sol | 89.7% 88.5 to 90.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 12 | | 88.7% 88.5 to 89 | high | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 13 | | 88.5% ±1 | high | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 14 | GPT-6 Sol | 87.8% 86 to 89 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 15 | GPT-5.6 Terra | 86.7% 85.5 to 87.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 16 | GPT-5.5 | 86.5% 85 to 87.5 | xhigh | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 17 | | 85.5% 84.5 to 87 | high | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 18 | | 84% ±0.5 | high | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 19 | | 83.7% 81.5 to 85 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 20 | GPT-5.4 | 83% ±0.5 | xhigh | Mar 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 21 | Claude Opus 4.8 | 82.7% 77 to 85.5 | max | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 22 | | 81.3% 80.5 to 82 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 23 | | 80.5% 79 to 81.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 24 | Claude Haiku 5.5 | 80.2% 79.5 to 80.5 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 25 | GLM-5.3-Flash | 79.8% 79.5 to 80 | max | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 26 | | 79.3% 76.5 to 81.5 | high | Dec 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 27 | | 77.7% 76.5 to 78.5 | high | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 28 | | 77.3% ±4.3 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 29 | GPT-5.6 Luna | 77% 75 to 78.5 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 30 | Grok 4.6 | 75.8% 74 to 78.5 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 31 | GPT-6 Luna | 75.5% 75 to 76.5 | max | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 32 | Grok 4.5 | 74.5% ±1.5 | high | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 33 | GPT-5.2 | 73.7% 71.5 to 75 | xhigh | Dec 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 34 | Kimi K3 | 73.5% 70.5 to 76 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 35 | | 72.7% 70 to 78 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 36 | | 71.8% 69 to 74 | max | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 37 | Grok 4.7 | 71.2% 70 to 72 | xhigh | Sep 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 38 | | 70.3% 68.5 to 71.5 | high | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 39 | | 69.2% 68 to 70.5 | thinking | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 40 | | 67% 64.5 to 68.5 | xhigh | Aug 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 41 | GPT-5.4 Mini | 66.8% 64.5 to 69.5 | xhigh | Mar 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 42 | | 65% 63.5 to 66 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 43 | Kimi K2.7 Code | 64.2% 60.5 to 66.5 | thinking | Jun 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 44 | Claude Sonnet 4.6 | 62.2% 61.5 to 63 | max | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 45 | | 58.5% 56.5 to 62 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 46 | | 56.8% 56 to 57.5 | max | Jun 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 47 | GPT-5.1 | 55% 52.5 to 59.5 | high | Nov 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 48 | GPT-5 | 53.3% 51.5 to 55 | high | Aug 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 49 | Claude Opus 4.5 | 52.8% 50 to 54.5 | max | Nov 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 50 | o3 | 51.5% ±1.5 | high | Apr 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 51 | | 51.5% 47 to 55 | max | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 52 | | 48.7% 42.5 to 54 | max | Jul 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 53 | | 47.5% 45 to 50.5 | high | May 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 54 | | 46% 44.5 to 48.5 | default | Apr 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 55 | Claude Sonnet 4.5 | 44.2% 42.5 to 46.5 | max | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 56 | | 43.2% 42 to 44 | thinking | Feb 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 57 | | 42.5% | max | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 58 | | 37.5% 35 to 39.5 | max | Oct 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 59 | | 36.5% 33.5 to 40 | high | Apr 2026 | razavi-bench.tokenzhang.com | Official leaderboard |
| 60 | | 36% 33 to 38 | default | Sep 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 61 | Claude Haiku 4.5 | 31.2% 27.5 to 33.5 | max | Oct 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 62 | | 26.3% 25 to 27 | default | Jan 2025 | razavi-bench.tokenzhang.com | Official leaderboard |
| 63 | GPT-4o mini | 25.7% 24.5 to 27 | default | Jul 2024 | razavi-bench.tokenzhang.com | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Part 1 and Part 2. Each ranks models on one part of the test. Claude Opus 5.5 leads Part 1 and Gemini 4 Carbon leads Part 2. Arrows show how far a model moved from its overall rank among the models we track.
Part 1
63 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 100%
- 2 Claude Fable 5.2 ↑1 100%
- 3 Claude Fable 5.1 ↑4 99.7%
- 4 GPT-6 Astra ↑1 99.7%
- 5
Gemini 4 Carbon ↓4 99.7%
- 6 GPT-6.1 Sol ↑2 99.4%
- 7 Claude Fable 5 ↑2 98.9%
- 8
Gemini 3.8 Flash ↑4 98.6%
- 9
Gemini 4 Argon ↓5 98.3%
- 10
Gemini 3.7 Flash ↑3 98.1%
Part 2
63 models we track have a score here.
- 1
Gemini 4 Carbon 96.3%
- 2 Claude Opus 5.5 94.2%
- 3
Gemini 4 Argon ↑1 89.6%
- 4 Claude Fable 5.2 ↓1 89.6%
- 5 Claude Opus 5 ↑1 88.8%
- 6 GPT-6 Astra ↓1 87.1%
- 7 GPT-5.6 Sol ↑4 86.3%
- 8 Claude Fable 5.1 ↓1 84.6%
- 9
Tencent Hy4 ↑1 84.2%
- 10 GPT-6.1 Sol ↓2 82.9%
The best score, 98.3%, costs $28 for the full run
Runs on the cost frontier score higher than any run that's cheaper. Gemini 4 Argon at high comes within 3.5 points of the best for $8.19 for the full run, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Razavi-Bench leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| high | 98.3% | $28 | |||
| Claude Opus 5.5 | max | 97.7% | $68 | ||
| Claude Fable 5.2 | max | 95.8% | $51 | ||
| high | 94.8% | $8.19 | |||
| GPT-6 Astra | max | 94.7% | $43 | ||
| Claude Opus 5 | max | 94% | $28 | ||
| Claude Fable 5.1 | max | 93.7% | $93 | ||
| GPT-6.1 Sol | max | 92.8% | $8.34 | ||
| Claude Fable 5 | max | 90.5% | $79 | ||
| high | 90.3% | $4.77 | |||
| GPT-5.6 Sol | max | 89.7% | $35 | ||
| high | 88.7% | $7.28 | |||
| high | 88.5% | $2.73 | |||
| GPT-6 Sol | max | 87.8% | $8.14 | ||
| GPT-5.6 Terra | max | 86.7% | $35 | ||
| GPT-5.5 | xhigh | 86.5% | $39 | ||
| high | 85.5% | $7.94 | |||
| high | 84% | $2.95 | |||
| xhigh | 83.7% | $6.61 | |||
| GPT-5.4 | xhigh | 83% | $32 | ||
| Claude Opus 4.8 | max | 82.7% | $76 | ||
| xhigh | 81.3% | $9.15 | |||
| max | 80.5% | $7.57 | |||
| Claude Haiku 5.5 | max | 80.2% | $4.68 | ||
| GLM-5.3-Flash | max | 79.8% | $2.74 | ||
| high | 79.3% | $2.41 | |||
| high | 77.7% | $23 | |||
| max | 77.3% | $1.92 | |||
| GPT-5.6 Luna | max | 77% | $3.36 | ||
| Grok 4.6 | xhigh | 75.8% | $5.81 | ||
| GPT-6 Luna | max | 75.5% | $0.93 | ||
| Grok 4.5 | high | 74.5% | $4.55 | ||
| GPT-5.2 | xhigh | 73.7% | $39 | ||
| Kimi K3 | max | 73.5% | $34 | ||
| max | 72.7% | $1.62 | |||
| max | 71.8% | $1.65 | |||
| Grok 4.7 | xhigh | 71.2% | $13 | ||
| high | 70.3% | $6.31 | |||
| thinking | 69.2% | $3.46 | |||
| xhigh | 67% | $3.63 | |||
| GPT-5.4 Mini | xhigh | 66.8% | $13 | ||
| max | 65% | $0.22 | |||
| Kimi K2.7 Code | thinking | 64.2% | $5.60 | ||
| Claude Sonnet 4.6 | max | 62.2% | $68 | ||
| max | 58.5% | $4.02 | |||
| max | 56.8% | $8.22 | |||
| GPT-5.1 | high | 55% | $14 | ||
| GPT-5 | high | 53.3% | $13 | ||
| Claude Opus 4.5 | max | 52.8% | $20 | ||
| o3 | high | 51.5% | $5.90 | ||
| max | 51.5% | $0.23 | |||
| max | 48.7% | $11 | |||
| high | 47.5% | $17 | |||
| default | 46% | $0.18 | |||
| Claude Sonnet 4.5 | max | 44.2% | $7.54 | ||
| thinking | 43.2% | $0.70 | |||
| max | 42.5% | $2.72 | |||
| max | 37.5% | $1.26 | |||
| high | 36.5% | $7.77 | |||
| default | 36% | $0.39 | |||
| Claude Haiku 4.5 | max | 31.2% | $3.02 | ||
| default | 26.3% | $0.31 | |||
| GPT-4o mini | default | 25.7% | $0.56 |
The best score, 98.3%, costs $28 for the full run
Runs on the cost frontier score higher than any run that's cheaper. Gemini 4 Argon at high comes within 3.5 points of the best for $8.19 for the full run, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Razavi-Bench leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| high | 98.3% | $28 | |||
| Claude Opus 5.5 | max | 97.7% | $68 | ||
| Claude Fable 5.2 | max | 95.8% | $51 | ||
| high | 94.8% | $8.19 | |||
| GPT-6 Astra | max | 94.7% | $43 | ||
| Claude Opus 5 | max | 94% | $28 | ||
| Claude Fable 5.1 | max | 93.7% | $93 | ||
| GPT-6.1 Sol | max | 92.8% | $8.34 | ||
| Claude Fable 5 | max | 90.5% | $79 | ||
| high | 90.3% | $4.77 | |||
| GPT-5.6 Sol | max | 89.7% | $35 | ||
| high | 88.7% | $7.28 | |||
| high | 88.5% | $2.73 | |||
| GPT-6 Sol | max | 87.8% | $8.14 | ||
| GPT-5.6 Terra | max | 86.7% | $35 | ||
| GPT-5.5 | xhigh | 86.5% | $39 | ||
| high | 85.5% | $7.94 | |||
| high | 84% | $2.95 | |||
| xhigh | 83.7% | $6.61 | |||
| GPT-5.4 | xhigh | 83% | $32 | ||
| Claude Opus 4.8 | max | 82.7% | $76 | ||
| xhigh | 81.3% | $9.15 | |||
| max | 80.5% | $7.57 | |||
| Claude Haiku 5.5 | max | 80.2% | $4.68 | ||
| GLM-5.3-Flash | max | 79.8% | $2.74 | ||
| high | 79.3% | $2.41 | |||
| high | 77.7% | $23 | |||
| max | 77.3% | $1.92 | |||
| GPT-5.6 Luna | max | 77% | $3.36 | ||
| Grok 4.6 | xhigh | 75.8% | $5.81 | ||
| GPT-6 Luna | max | 75.5% | $0.93 | ||
| Grok 4.5 | high | 74.5% | $4.55 | ||
| GPT-5.2 | xhigh | 73.7% | $39 | ||
| Kimi K3 | max | 73.5% | $34 | ||
| max | 72.7% | $1.62 | |||
| max | 71.8% | $1.65 | |||
| Grok 4.7 | xhigh | 71.2% | $13 | ||
| high | 70.3% | $6.31 | |||
| thinking | 69.2% | $3.46 | |||
| xhigh | 67% | $3.63 | |||
| GPT-5.4 Mini | xhigh | 66.8% | $13 | ||
| max | 65% | $0.22 | |||
| Kimi K2.7 Code | thinking | 64.2% | $5.60 | ||
| Claude Sonnet 4.6 | max | 62.2% | $68 | ||
| max | 58.5% | $4.02 | |||
| max | 56.8% | $8.22 | |||
| GPT-5.1 | high | 55% | $14 | ||
| GPT-5 | high | 53.3% | $13 | ||
| Claude Opus 4.5 | max | 52.8% | $20 | ||
| o3 | high | 51.5% | $5.90 | ||
| max | 51.5% | $0.23 | |||
| max | 48.7% | $11 | |||
| high | 47.5% | $17 | |||
| default | 46% | $0.18 | |||
| Claude Sonnet 4.5 | max | 44.2% | $7.54 | ||
| thinking | 43.2% | $0.70 | |||
| max | 42.5% | $2.72 | |||
| max | 37.5% | $1.26 | |||
| high | 36.5% | $7.77 | |||
| default | 36% | $0.39 | |||
| Claude Haiku 4.5 | max | 31.2% | $3.02 | ||
| default | 26.3% | $0.31 | |||
| GPT-4o mini | default | 25.7% | $0.56 |
14 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Razavi-Bench leaderboard
GPT-5.5 on the official leaderboard passed 85% in April 2026
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Razavi-Bench 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%
- 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%
- 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (73 entries).
- Pass Models scored 63 models we track, plus 10 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
- Pass Frontier models 7 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Saturated. The best is 98.3%, past 85% since April 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on razavi-bench.tokenzhang.com: 63 rows for models we track and 10 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.