Benchmarks · agentic
SkillsBench
How important are skills for agents? Vals AI's overall SkillsBench score.
31 models · 31 results · updated 2026-10-29 · vals.ai ↗
Leaderboard
DeepSeek V4.1 Flash high
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 19 more models under All models in settings.
More from this benchmark
1 published measuresTime per task35 results · lower is better
18 more models under All models in settings.
All results
31 rows| # | Model | Effort | SkillsBench | Subscription $ / task | API $ / task | Time | Harness |
|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash | high | 69.8% | $0.006 | $0.085 | 3.7 min | OpenHands |
| 2 | Grok 4.5 | high | 66.0% | $0.091 | $0.58 | 2.3 min | OpenHands |
| 3 | Gemini 3.7 Flash | high | 65.9% | $0.23 | $1.80 | 3.1 min | OpenHands |
| 4 | GPT-5.5 | xhigh | 62.2% | $0.070 | $2.54 | 6.9 min | OpenHands |
| 5 | Fable 5.1 | max | 61.6% | $0.70 | $4.52 | 11 min | OpenHands |
| 6 | GPT-5.6 Luna | max | 60.4% | $0.010 | $0.21 | 5.3 min | OpenHands |
| 7 | Opus 5 | max | 60.4% | $0.043 | $2.51 | 8.4 min | OpenHands |
| 8 | Opus 4.8 | max | 59.2% | $0.083 | $4.77 | 16 min | OpenHands |
| 9 | Muse Spark 1.1 | xhigh | 59.2% | $0.45 | $0.45 | 6.3 min | OpenHands |
| 10 | GPT-5.6 Terra | max | 58.9% | $0.048 | $1.75 | 6.9 min | OpenHands |
| 11 | Gemini 3.8 Flash | high | 58.0% | $0.095 | $2.34 | 3.9 min | OpenHands |
| 12 | Grok 4.6 | high | 55.8% | $0.095 | $0.92 | 13 min | OpenHands |
| 13 | Qwen 3.7 Plus | high | 54.3% | $0.21 | $0.14 | 12 min | OpenHands |
| 14 | GPT-5.6 Sol | max | 54.1% | $0.11 | $4.14 | 13 min | OpenHands |
| 15 | DeepSeek V4 Pro 0813 | max | 53.8% | $0.37 | $0.37 | 11 min | OpenHands |
| 16 | Muse Spark 1.2 | xhigh | 53.0% | $0.32 | $0.65 | 13 min | OpenHands |
| 17 | Gemini 3.5 Flash | high | 52.7% | $1.25 | $1.25 | 7.3 min | OpenHands |
| 18 | MiniMax M3 | max | 51.5% | $0.085 | $0.50 | 15 min | OpenHands |
| 19 | DeepSeek V4 Flash 0731 | high | 50.7% | $0.13 | $0.13 | 6.9 min | OpenHands |
| 20 | Kimi K2.7 Code | max | 50.0% | $0.097 | $0.44 | 13 min | OpenHands |
| 21 | Sonnet 4.6 | max | 49.1% | $1.38 | $1.38 | 14 min | OpenHands |
| 22 | GLM 5.3 | max | 47.5% | $0.074 | $0.71 | 13 min | OpenHands |
| 23 | Sonnet 5 | max | 46.5% | $0.050 | $2.90 | 15 min | OpenHands |
| 24 | GLM 5.2 | max | 45.1% | $0.024 | $0.81 | 20 min | OpenHands |
| 25 | Qwen 3.8 Max | max | 42.0% | $0.062 | $0.52 | 16 min | OpenHands |
| 26 | Grok 4.3 | high | 40.6% | $0.42 | $0.42 | 4.6 min | OpenHands |
| 27 | GLM 5.3 Flash | max | 40.2% | free | $0.078 | 12 min | OpenHands |
| 28 | Qwen 3.8 27B | xhigh | 38.1% | $0.060 | $0.82 | 6.7 min | OpenHands |
| 29 | Inkling Small | max | 33.6% | $0.12 | $0.15 | 12 min | OpenHands |
| 30 | Inkling | max | 26.1% | $0.076 | $0.83 | 16 min | OpenHands |