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

OpenHarmony Bench v1.0 (OpenHarmony Bench)

An app-level coding benchmark that asks DevEco Code configurations to implement observable behavior in buildable OpenHarmony ArkTS applications.

Data verified 22 confirmed releases in the last 30 daysStart free brief

Benchmark score on OpenHarmony Bench — August 24, 2026

We mirror the published score view for OpenHarmony Bench. Qwen3.8 Max leads the public snapshot at 60.8%, followed by GLM-5.3 (60.8%) and GLM-5.2 (58.4%). We do not use these results to rank models overall.

1Open

Qwen3.8 Max

Alibaba

60.8%
Overall 78.92Context 1M
2Closed

GLM-5.3

Z.AI

60.8%
Overall 62.55Context 1M
3Open

GLM-5.2

Z.AI

58.4%
Overall 63.02Context 1M
11 modelsCodingCurrentDisplay onlyUpdated August 24, 2026

Benchmark score table (11 models)

Score
1
Qwen3.8 MaxAlibaba · Open weight
60.8%
2
GLM-5.3Z.AI · Closed
60.8%
3
GLM-5.2Z.AI · Open weight
58.4%
4
Kimi K3Moonshot AI · Closed
57.3%
5
Qwen3.8 Max PreviewAlibaba · Closed
56.0%
6
DeepSeek V4 Flash 0731DeepSeek · Closed
53.8%
7
Qwen3.7 MaxAlibaba · Closed
53.4%
8
GLM-5.1Z.AI · Open weight
52.3%
9
Kimi K2.7 CodeMoonshot AI · Open weight
52.1%
10
DeepSeek V4 ProDeepSeek · Open weight
52.1%
11
MiniMax M3MiniMax · Open weight
48.4%

The published OpenHarmony Bench snapshot places Qwen3.8 Max first at 60.8%. The third row is 2.4 points behind. The broader top-10 range is 8.7 points, so many of the published results sit in a relatively narrow band.

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

About OpenHarmony Bench

Year

2026

Tasks

153 app-development and bug-fix tasks

Format

Task completion through DevEco Code

Difficulty

End-to-end OpenHarmony application development

The v1.0 snapshot contains 153 top-level tasks and 242 executable feature checks across 42 repositories. Each leaderboard row averages three full-suite DevEco Code runs. We store Task Completion as display-only model-plus-agent evidence; build rates, duration, token use, and run ranges remain in the source snapshot.

OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development

BenchLM freshness & provenance

Version

OpenHarmony Bench 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 OpenHarmony Bench measure?

An app-level coding benchmark that asks DevEco Code configurations to implement observable behavior in buildable OpenHarmony ArkTS applications.

Which model scores highest on OpenHarmony Bench?

Qwen3.8 Max by Alibaba currently leads with a score of 60.8% on OpenHarmony Bench.

How many models are evaluated on OpenHarmony Bench?

11 AI models have been evaluated on OpenHarmony Bench on BenchLM.

Compare Top Models on OpenHarmony Bench

Qwen3.8 Max vs GLM-5.3GLM-5.3 vs GLM-5.2GLM-5.2 vs Kimi K3Kimi K3 vs Qwen3.8 Max Preview
Last updated: August 24, 2026 · BenchLM version OpenHarmony Bench 2026

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.