Benchmark Almanac

NotSoTiny 25-12

Kimi K2.5 31.6% leads since January 2026
Not in model cards

Models reconstruct a missing Verilog module from surrounding hardware design code. A formal checker compares the result with the original module.

The authors publish scores for 15 model entries across seven Tiny Tapeout collections. The release contains 1,114 module completion tasks.

Released
December 2025
Kind
Electronics
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Code → Code
Interaction
Single turn
Items from
Real work and use
Run by
Anyone
Strongest model tested
Kimi K2.5 #76 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 9 models we track

Kimi K2.5 leads with 31.6% among models released by April 2026 Kimi K2.5 leads with 31.6% among models released by April 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. 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 April 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 Kimi K2.5 31.6%
  2. 2 Gemma 4 31B IT 29.5%
  3. 3 Qwen3-Coder-480B-A35B 23.4%
  4. 4 gpt-oss-120b 20.9%
  5. 5 DeepSeek-R1 May 2025 20.7%
  6. 6 Kimi K2 Sep 2025 19%
  7. 7 InCoder-32B 19%
  8. 8 Qwen2.5-72B 14.7%
  9. 9 InCoder-32B-Thinking 13.1%
  10. 10 Qwen2.5-14B-Instruct-1M 12.5%
  11. 11 Qwen2.5-Coder-32B-Instruct 11.8%
  12. 12 Qwen2.5-14B-Instruct 8.97%
  13. 13 HaVen-CodeQwen 4.20%
  14. 14 Qwen2.5-7B-Instruct 3.48%
  15. 15 OriGen 3.31%

Source: Official NotSoTiny 25-12 leaderboard

#EntryScoreSettingDateSource
1 Kimi K2.5 31.6% Jan 2026 Official leaderboard
2 Gemma 4 31B IT 29.5% Apr 2026 Official leaderboard
3 Qwen3-Coder-480B-A35B 23.4% Jul 2025 Official leaderboard
4 gpt-oss-120b 20.9% Aug 2025 Official leaderboard
5 DeepSeek-R1 May 2025 20.7% May 2025 Official leaderboard
6 Kimi K2 Sep 2025 19% Sep 2025 Official leaderboard
7 InCoder-32B 19% Official leaderboard
8 Qwen2.5-72B 14.7% Sep 2024 Official leaderboard
9 InCoder-32B-Thinking 13.1% Official leaderboard
10 Qwen2.5-14B-Instruct-1M 12.5% Jan 2025 Official leaderboard
11 Qwen2.5-Coder-32B-Instruct 11.8% Nov 2024 Official leaderboard
12 Qwen2.5-14B-Instruct 8.97% Official leaderboard
13 HaVen-CodeQwen 4.20% Official leaderboard
14 Qwen2.5-7B-Instruct 3.48% Official leaderboard
15 OriGen 3.31% Official leaderboard
#ModelScoreSettingDateSource
1 Kimi K2.5 31.6% Jan 2026 Official leaderboard
2 Gemma 4 31B IT 29.5% Apr 2026 Official leaderboard
3 Qwen3-Coder-480B-A35B 23.4% Jul 2025 Official leaderboard
4 gpt-oss-120b 20.9% Aug 2025 Official leaderboard
5 DeepSeek-R1 May 2025 20.7% May 2025 Official leaderboard
6 Kimi K2 Sep 2025 19% Sep 2025 Official leaderboard
7 Qwen2.5-72B 14.7% Sep 2024 Official leaderboard
8 Qwen2.5-14B-Instruct-1M 12.5% Jan 2025 Official leaderboard
9 Qwen2.5-Coder-32B-Instruct 11.8% Nov 2024 Official leaderboard

Rankings by part

We read 7 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as TT06, TT07 and TT08. Kimi K2.5 leads 4 of them, and Gemma 4 31B IT leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.

2 models have held number one on the official leaderboard since its release in December 2025

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

Qwen Moonshot AI
Own leaderboard Not tested since Apr 2026
Kimi K2.5 31.6%

Source: Official NotSoTiny 25-12 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%) Kimi K2.5 Qwen3-Coder-480B-A35B Qwen2.5-72B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Kimi K2.5 Qwen3-Coder-480B-A35B

Source: Official NotSoTiny 25-12 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Gemma 4 31B IT. Every benchmark

Catalog record 2 pass
  • Pass Task access All 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 (15 entries).
  • Pass Models scored 9 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 7 months ago, in April 2026, for Gemma 4 31B IT.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K2.5 (#76).
  • Pass Headroom The best is 31.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 9 rows for models we track and 6 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.

How we check