Benchmark Almanac

HWE-bench CAE

GPT-5.6 Sol 0.90% leads since August 2026
Not in model cards

Agents run engineering simulations, extract numerical results, and report them. A verifier repeats the extraction from the solver output and checks engineering tolerances.

The August 2026 CAE-bench leaderboard compares eight models across 77 tasks in four engineering domains. GPT-5.6 Sol led with a domain-weighted mean of 0.898.

Made by
svd-ai-lab
Released
August 2026
Kind
CAD models
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
A simulator
Refresh
One fixed set
Run by
Anyone
In views
Agents, Robotics
Strongest model tested
GPT-5.6 Sol #14 on the capability index
Last model added
July 2026
Scores refreshed
November 21st, 2026
8
Models scored on its own leaderboard

GPT-5.6 Sol leads with 0.90% among models released by July 2026

Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in July 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-5.6 Sol 0.90%
  2. 2 Kimi K3 0.84%
  3. 3 Claude Sonnet 5 0.72%
  4. 4 DeepSeek-V4-Flash 0.67%
  5. 5 Doubao Seed 2.1 Turbo 0.64%
  6. 6 GPT-5.6 Luna 0.60%
  7. 7 MiniMax-M3 0.49%
  8. 8 Doubao Seed 2.0 Lite Apr 2026 0.31%

Source: Official HWE-bench CAE leaderboard

#ModelScore ±SettingDateSource
1 GPT-5.6 Sol 0.90% ±0.1 terminus-2 Jul 2026 Official leaderboard
2 Kimi K3 0.84% ±0.1 terminus-2 Jul 2026 Official leaderboard
3 Claude Sonnet 5 0.72% ±0 terminus-2 Jun 2026 Official leaderboard
4 DeepSeek-V4-Flash 0.67% ±0.1 terminus-2 Apr 2026 Official leaderboard
5 Doubao Seed 2.1 Turbo 0.64% ±0.1 terminus-2 Jun 2026 Official leaderboard
6 GPT-5.6 Luna 0.60% ±0.1 terminus-2 Jul 2026 Official leaderboard
7 MiniMax-M3 0.49% ±0.1 terminus-2 Jun 2026 Official leaderboard
8 Doubao Seed 2.0 Lite Apr 2026 0.31% ±0.1 terminus-2 Apr 2026 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Combustion, Battery and CFD. Claude Sonnet 5 leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Combustion

8 models we track have a score here.

  1. 1 Doubao Seed 2.1 Turbo ↑4 1.00%
  2. 2 GPT-5.6 Sol ↓1 1.00%
  3. 3 Claude Sonnet 5 0.95%
  4. 4 DeepSeek-V4-Flash 0.90%
  5. 5 Kimi K3 ↓3 0.90%
  6. 6 GPT-5.6 Luna 0.88%
  7. 7 MiniMax-M3 0.86%
  8. 8 Doubao Seed 2.0 Lite Apr 2026 0.76%

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 Aug 2026
GPT-5.6 Sol 0.90%

Source: Official HWE-bench CAE 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% 2026 Near the ceiling (85%) GPT-5.6 Sol DeepSeek-V4-Flash 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol

Source: Official HWE-bench CAE 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

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 (8 entries).
  • Pass Models scored 8 models we track.
  • Pass Newest score The newest is from July 2026, for Kimi K3.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.6 Sol (#14).
  • Pass Headroom The best is 0.90%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on cae-bench.svdailab.com: 8 rows for models we track at the last read.
  • Pass Last read November 21st, 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