Benchmark Almanac

HWE Bench V1 (RISC-V CPU design)

Claude Opus 5.5 983.2 leads since September 2026
Not in model cards
Version 1

Agents improve a RISC-V processor in Verilog. Designs must pass correctness checks before the benchmark ranks them by estimated CoreMark iterations per second.

V1 uses nextpnr to estimate clock speed. The author later found missing timing paths that inflated the scores.

Released
May 2026
Kind
Electronics
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Written by experts
Run by
Anyone
In views
Agents
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
13
Entries on its own leaderboard, 12 models we track

Claude Opus 5.5 leads with 983.2 among models released by September 2026 Claude Opus 5.5 leads with 983.2 among models released by September 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 September 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 Claude Opus 5.5 xhigh 983.2
  2. 2 GPT-5.5 xhigh 525.0
  3. 3 GPT-5.6 Terra 515.7
  4. 4 GPT-5.4 xhigh 513.8
  5. 5 GPT-5.6 Luna 480.9
  6. 6 GPT-6 Astra max 474.3
  7. 7 GPT-5.6 Sol 470.8
  8. 8 GPT-6 Sol xhigh 435.2
  9. 9 Kimi K2.6 396.1
  10. 10 GPT-5.4 Mini 395.5
  11. 11 Gemini 3.5 Flash 359.0
  12. 12 Gemini 3.1 Pro 354.7
  13. 13 static 282.8

Source: Official HWE Bench V1 (RISC-V CPU design) leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 5.5 983.2 xhigh Sep 2026 Official leaderboard
2 GPT-5.5 525.0 xhigh Apr 2026 Official leaderboard
3 GPT-5.6 Terra 515.7 Jul 2026 Official leaderboard
4 GPT-5.4 513.8 xhigh Mar 2026 Official leaderboard
5 GPT-5.6 Luna 480.9 Jul 2026 Official leaderboard
6 GPT-6 Astra 474.3 max Sep 2026 Official leaderboard
7 GPT-5.6 Sol 470.8 Jul 2026 Official leaderboard
8 GPT-6 Sol 435.2 xhigh Sep 2026 Official leaderboard
9 Kimi K2.6 396.1 Apr 2026 Official leaderboard
10 GPT-5.4 Mini 395.5 Mar 2026 Official leaderboard
11 Gemini 3.5 Flash 359.0 May 2026 Official leaderboard
12 Gemini 3.1 Pro 354.7 Feb 2026 Official leaderboard
13 static 282.8 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5.5 983.2 xhigh Sep 2026 Official leaderboard
2 GPT-5.5 525.0 xhigh Apr 2026 Official leaderboard
3 GPT-5.6 Terra 515.7 Jul 2026 Official leaderboard
4 GPT-5.4 513.8 xhigh Mar 2026 Official leaderboard
5 GPT-5.6 Luna 480.9 Jul 2026 Official leaderboard
6 GPT-6 Astra 474.3 max Sep 2026 Official leaderboard
7 GPT-5.6 Sol 470.8 Jul 2026 Official leaderboard
8 GPT-6 Sol 435.2 xhigh Sep 2026 Official leaderboard
9 Kimi K2.6 396.1 Apr 2026 Official leaderboard
10 GPT-5.4 Mini 395.5 Mar 2026 Official leaderboard
11 Gemini 3.5 Flash 359.0 May 2026 Official leaderboard
12 Gemini 3.1 Pro 354.7 Feb 2026 Official leaderboard

2 models have held number one on the official leaderboard since its release in May 2026

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

OpenAI Anthropic
Own leaderboard Replaced by V2 (RISC-V CPU design), Oct 2026

Source: Official HWE Bench V1 (RISC-V CPU design) 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
200.0 400.0 600.0 800.0 1000.0 2026 200.0 400.0 600.0 800.0 1000.0 2026

Source: Official HWE Bench V1 (RISC-V CPU design) 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.

Versions

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 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 (13 entries).
  • Pass Models scored 12 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
  • Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on hwebench.com: 14 rows for models we track and 1 other entry 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