Skip to content

Benchmark

SkillsBench · Self-contained subset

Scores are percentages. Higher is better.

Models and systems measured
8
Scores recorded
9
Sources
1
IQ weight
No weight published

Score distribution

49.3%
Mean
52.3%
Median
8.5%
Std dev
45.7%
10th percentile
56.2%
90th percentile
28.7%
Min
28.7%59.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Qwen3.7 MaxQwen3.7-Max release · OpenCode · 78 tasks after excluding 9 external-API tasks · avg@5· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.2%
2Kimi K2.6Qwen3.7 release comparison table · OpenCode · 78 tasks excluding 9 external-API tasks · five-run average · table effort=Thinking· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.2%
3Qwen3.7 PlusQwen3.7-Plus release · OpenCode · 78 tasks after excluding 9 external-API tasks · avg@5· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.9%
4GLM 5.1Qwen3.7 release comparison table · OpenCode · 78 tasks excluding 9 external-API tasks · five-run average · table effort=Thinking· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.1%
5Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · OpenCode · 78 self-contained tasks · five-run average· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.2%
6Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · OpenCode · 78 self-contained tasks · five-run average· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.7%
7Qwen3.6 PlusQwen3.7 release comparison table · OpenCode · 78 tasks excluding 9 external-API tasks · five-run average · table effort=not stated· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.7%
8Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.28.7%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4 Pro (version unspecified)Qwen3.7 release comparison table · OpenCode · 78 tasks excluding 9 external-API tasks · five-run average · table effort=Max· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.3%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.