Benchmark Almanac

SimReadyBench NV100

GPT-6.1 Sol 100% leads since October 2026
Not in model cards

Agents reconstruct an articulated 3D asset from one image and nominal dimensions. The verifier grades formal, visual, and kinematic fidelity separately across 100 assets.

On November 19, 2026, two GPT-6.1 Sol configurations tied at 100% formal fidelity. The table also reports Claude Opus, Claude Sonnet, and DeepSeek.

Released
October 2026
Kind
CAD models
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → 3D, Actions
Interaction
Agentic
Environment
A simulator
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
7
Models scored on its own leaderboard

2 models share the top score of 100%

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

  1. 1 GPT-6.1 Sol high 100%
  2. 2 GPT-6.1 Terra high 100%
  3. 3 GPT-6.2 Astra low 99.6%
  4. 4 Claude Opus 5.5 low 97.1%
  5. 5 DeepSeek V4.1 Flash 1017 none 86.3%
  6. 6 Claude Sonnet 5.5 low 83.6%
  7. 7 Nemotron 3.5 Super VL none 76.7%

Source: Official SimReadyBench NV100 leaderboard

#ModelScoreSettingDateSource
1 GPT-6.1 Sol 100% high, Codex Sep 2026 Official leaderboard
2 GPT-6.1 Terra 100% high, Codex Oct 2026 Official leaderboard
3 GPT-6.2 Astra 99.6% low, Codex Nov 2026 Official leaderboard
4 Claude Opus 5.5 97.1% low, Claude Code Sep 2026 Official leaderboard
5 DeepSeek V4.1 Flash 1017 86.3% none, Terminus 2 Oct 2026 Official leaderboard
6 Claude Sonnet 5.5 83.6% low, Claude Code Sep 2026 Official leaderboard
7 Nemotron 3.5 Super VL 76.7% none, Terminus 2 Oct 2026 Official leaderboard

The best score, 100%, costs $0.27 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI DeepSeek Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.02 $0.05 $0.10 $0.20 $0.50 $1.00 Cost per task, log scale GPT-6.1 Terra, high GPT-6.1 Terra, low DeepSeek V4.1 Flash 1017, none 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra, high GPT-6.1 Terra, low

Source: Official SimReadyBench NV100 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.1 Sol high Codex 100% $0.71 31,221
GPT-6.1 Sol medium Codex + CAD/build123d 100% $0.74 17,811
GPT-6.1 Terra high Codex 100% $0.27 19,776
GPT-6.1 Terra medium Codex + CAD/build123d 100% $0.40 15,487
GPT-6.1 Sol medium Codex 99.98% $0.41 18,404
GPT-6.2 Astra low Codex 99.6% $0.58 4,907
GPT-6.1 Sol low Codex 97.7% $0.21 7,728
Claude Opus 5.5 low Claude Code 97.1% $0.31 6,901
GPT-6.1 Terra low Codex 91.1% $0.10 5,575
DeepSeek V4.1 Flash 1017 none Terminus 2 86.3% $0.03 31,914
DeepSeek V4.1 Flash 1017 none Terminus 2 + CAD/build123d 86.3% $0.03 34,188
Claude Sonnet 5.5 low Claude Code 83.6% $0.06 2,359
Nemotron 3.5 Super VL none Terminus 2 76.7% $0.34 47,136

Number one over time

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

OpenAI
Own leaderboard Passed 85% in Oct 2026, by GPT-6.1 Sol

Source: Official SimReadyBench NV100 leaderboard

Claude Opus 5.5 on the official leaderboard passed 85% in September 2026

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.1 Sol 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.1 Sol

Source: Official SimReadyBench NV100 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 (7 entries).
  • Pass Models scored 7 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Saturated. The best is 100%, past 85% since September 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 13 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check