Skip to main content

Vals SkillsBench (SkillsBench)

How important are skills for agents?

Data verified

How BenchLM shows SkillsBench

BenchLM mirrors the public Vals AI SkillsBench leaderboard captured from https://www.vals.ai/benchmarks/skillsbench and updated by Vals on June 24, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

SkillsBench is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

12 Vals rows3 task viewspublic datasetTasks: Overall, No Skills, With SkillsDisplay only

SkillsBench score on SkillsBench — June 24, 2026

BenchLM mirrors the published skillsbench score view for SkillsBench. GPT-5.5 Codex leads the public snapshot at 62.55% , followed by GPT-5.5 (62.21%) and Claude Opus 4.8 (59.23%). BenchLM does not use these results to rank models overall.

12 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated June 24, 2026

The published SkillsBench snapshot is tightly clustered at the top: GPT-5.5 Codex sits at 62.55%, while the third row is only 3.33 points behind. The broader top-10 spread is 13.50 points, so the benchmark still separates strong models even when the leaders cluster.

12 models have been evaluated on SkillsBench. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. SkillsBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About SkillsBench

Year

2026

Tasks

Agent skill-importance tasks

Format

Accuracy score

Difficulty

Agent skill evaluation

BenchLM mirrors the public Vals AI SkillsBench leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

SkillsBench 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.

SkillsBench score table (12 models)

1
GPT-5.5 Codexopenai/gpt-5.5-codex
62.55%
2
GPT-5.5openai/gpt-5.5
62.21%
3
Claude Opus 4.8anthropic/claude-opus-4-8
59.23%
4
Qwen3.7 Plusalibaba/qwen3.7-plus
54.30%
5
Gemini 3.5 Flashgoogle/gemini-3.5-flash
52.74%
6
GPT-5.4openai/gpt-5.4-2026-03-05
51.71%
7
MiniMax M3minimax/MiniMax-M3
51.50%
8
DeepSeek V4 Prodeepseek/deepseek-v4-pro
51.27%
9
Kimi K2.7 Codekimi/kimi-k2.7-code
50.04%
10
Claude Sonnet 4.6anthropic/claude-sonnet-4-6
49.05%
11
GLM 5.2zai/glm-5.2
45.08%
12
Grok 4.3grok/grok-4.3
40.64%

FAQ

What does SkillsBench measure?

How important are skills for agents?

Which model leads the published SkillsBench snapshot?

GPT-5.5 Codex currently leads the published SkillsBench snapshot with 62.55% skillsbench score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on SkillsBench?

12 AI models are included in BenchLM's mirrored SkillsBench snapshot, based on the public leaderboard captured on June 24, 2026.

Last updated: June 24, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.