llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeBenchmarksagentsSkillsBench

agents benchmark

SkillsBench

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

Updated Aug 7, 2026

Published models7
Registry coverage7
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

SkillsBench leaderboard

Sorted by the source-provided rank. Higher score is better according to the registry.

7 rows
Columns

Show columns

1ACQwen3.8 MaxAlibaba Cloud / Qwen Team70.2%100.0%7CAug 7, 2026
2ACQwen3.7 MaxAlibaba Cloud / Qwen Team59.2%83.3%7CAug 7, 2026
3TEHy3Tencent55.3%66.7%7CAug 7, 2026
4ACQwen3.7-PlusAlibaba Cloud / Qwen Team54.9%50.0%7CAug 7, 2026
5ACQwen3.6-27BAlibaba Cloud / Qwen Team48.2%33.3%7CAug 7, 2026
6ACQwen3.6 PlusAlibaba Cloud / Qwen Team45.7%16.7%7CAug 7, 2026
7ACQwen3.6-35B-A3BAlibaba Cloud / Qwen Team28.7%0.0%7CAug 7, 2026

Score distribution

Top published rows on the benchmark's original scale.

SkillsBench

SkillsBench highlights

The top published results on this benchmark's own scale.

Rank #1Qwen3.8 Max70.2%Rank #2Qwen3.7 Max59.2%Rank #3Hy355.3%Rank #4Qwen3.7-Plus54.9%

What is SkillsBench?

Definition and scoring fields from the benchmark registry.

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.

Family
SkillsBench
Modality
text
Primary category
agents
Score direction
higher
LLMBoard eligible
No
Evaluation key
skillsbench|llm-stats-current

Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.

FAQ

Common questions about SkillsBench.

Which model scores highest on SkillsBench?

Qwen3.8 Max is currently ranked first with 70.2%.

What does SkillsBench measure?

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

7 unique published model results are currently shown.

Does this benchmark affect the overall score?

This benchmark is preserved as source-native evidence but is not eligible for the current overall score.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai