Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Advertise

Benchmark profile

EEBench V1 core corpus (EEBench)

An electrical-engineering agent benchmark maintained by atopile.

How we show EEBench

We mirror the official EEBench V1 leaderboard generated on August 12, 2026 snapshot. The snapshot preserves all 30 published model-and-scaffold configurations together with uncertainty, attempt, cost, token, step, and duration fields.

EEBench is display only. The public results combine a model with scaffolds such as Claude Code, Grok CLI, Gemini CLI, API tools, or OpenRouter, so we keep them outside weighted model-only rankings.

30 configurations13 questions28 mapped rowsDisplay only
EEBench leaderboardPublished leaderboard data

EEBench score on EEBench — August 12, 2026 snapshot

BenchLM mirrors the published eebench score view for EEBench. Claude Opus 5 leads the public snapshot at 61.6% , followed by Grok 4.6 (58.3%) and Claude Fable 5 (54.3%). We do not use these results to rank models overall.

1Closed

Claude Opus 5

Anthropic

claude-opus-5-claude-code

61.6%
Overall 82.72
2Closed

Grok 4.6

xAI

grok-4-6-xhigh-grok-cli

58.3%
Overall 62.44Context 500K
3Closed

Claude Fable 5

Anthropic

claude-fable-5-claude-code

54.3%
Overall 82.54Context 1M+
30 modelsCodingCurrentDisplay onlyUpdated August 12, 2026 snapshot

EEBench score table (30 models)

Score
1
Claude Opus 5Anthropic · Closed
61.6%
2
Grok 4.6xAI · Closed
58.3%
3
Claude Fable 5Anthropic · Closed
54.3%
4
Claude Fable 5Anthropic · Closed
54.2%
5
Grok 4.6xAI · Closed
53.9%
6
Claude Opus 4.8Anthropic · Closed
51.4%
7
Grok 4.5xAI · Closed
50.9%
8
Gemini 3.1 ProGoogle · Closed
46.3%
9
GPT-5.5OpenAI · Closed
42.3%
10
Claude Sonnet 5Anthropic · Closed
40.3%
11
GPT-5.6 SolOpenAI · Closed
39.4%
12
GPT-5.4OpenAI · Closed
38.5%
13
Kimi K3Moonshot AI · Closed
38.3%
14
Gemini 3.6 FlashGoogle · Closed
37.4%
15
Claude Opus 4.8Anthropic · Closed
35.2%
16
Gemini 3.5 FlashGoogle · Closed
34.3%
17
GPT-5.6 Sol ProOpenAI
32.2%
18
GPT-5.6 TerraOpenAI · Closed
30.8%
19
Claude Sonnet 4.6Anthropic · Closed
20.4%
20
Gemini 3 FlashGoogle · Closed
19.5%
21
GPT-5.4 miniOpenAI · Closed
18.3%
22
Grok Build 0.1xAI · Closed
18.0%
23
GLM-5.2Z.AI · Open weight
16.7%
24
Grok 4.3xAI · Closed
14.3%
25
Kimi K2.7 CodeMoonshot AI · Open weight
12.8%
26
Qwen3.6 PlusAlibaba · Closed
12.7%
27
DeepSeek V4 ProDeepSeek · Closed
10.5%
28
MiniMax M3MiniMax · Open weight
9.2%
29
Mistral Medium 3.5Mistral
5.9%
30
Claude Haiku 4.5Anthropic · Closed
3.5%

The published EEBench snapshot places Claude Opus 5 first at 61.6%. The third row is 7.3 points behind. The broader top-10 range is 21.3 points, so the table still separates the published systems.

30 models have been evaluated on EEBench. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. EEBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About EEBench

Year

2026

Tasks

Electrical-engineering design tasks

Format

Agent task score

Difficulty

Professional electrical engineering

The public leaderboard exposes score, cost, and output-token fields. BenchLM stores the Grok 4.6 card comparison as display-only system evidence.

EEBench leaderboardPublic benchmark source

BenchLM freshness & provenance

Version

EEBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does EEBench measure?

An electrical-engineering agent benchmark maintained by atopile.

Which model leads the published EEBench snapshot?

Claude Opus 5 currently leads the published EEBench snapshot with 61.6% eebench score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on EEBench?

30 AI models are included in BenchLM's mirrored EEBench snapshot, based on the public leaderboard captured on August 12, 2026 snapshot.

Last updated: August 12, 2026 snapshot · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.