Benchmark Almanac

HWE Bench V2 (RISC-V CPU design)

Claude Opus 5.5 7024.2 leads since October 2026
Not in model cards
Version 2

Agents improve a RISC-V processor from a shared starting design. The benchmark scores throughput on five hidden programs using clock speeds from Gowin's timing tool.

Six agent systems each ran six times. The leaderboard ranks systems by the geometric mean of their held-out throughput in iterations per second.

Released
October 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
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
6
Models scored on its own leaderboard

Claude Opus 5.5 leads with 7024.2 among models released by September 2026

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.

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 7024.2
  2. 2 Claude Sonnet 5.5 6417.5
  3. 3 GPT-6.1 Sol 5320.1
  4. 4 GPT-6 Astra 5013.6
  5. 5 GPT-5.5 3594.8
  6. 6 GPT-6 Luna 3538.0

Source: Official HWE Bench V2 (RISC-V CPU design) leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 7024.2 Claude Code Sep 2026 Official leaderboard
2 Claude Sonnet 5.5 6417.5 Claude Code Sep 2026 Official leaderboard
3 GPT-6.1 Sol 5320.1 Codex CLI Sep 2026 Official leaderboard
4 GPT-6 Astra 5013.6 Codex CLI Sep 2026 Official leaderboard
5 GPT-5.5 3594.8 Codex CLI Apr 2026 Official leaderboard
6 GPT-6 Luna 3538.0 Codex CLI Sep 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard Not tested since Oct 2026

Source: Official HWE Bench V2 (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
3000.0 4000.0 5000.0 6000.0 7000.0 8000.0 2026 3000.0 4000.0 5000.0 6000.0 7000.0 8000.0 2026

Source: Official HWE Bench V2 (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 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 (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Pass Frontier models 4 of the top 10 have a score, led by 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: 6 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