Benchmark
SkillsBench 1.1 · With Skills
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 26
- Scores recorded
- 30
- Sources
- 1
- IQ weight
- 2.24
Score distribution
- 52.6%
- Mean
- 53.1%
- Median
- 12.2%
- Std dev
- 36.2%
- 10th percentile
- 67.3%
- 90th percentile
- 20.1%
- Min
This benchmark has a weight of 2.24 for chat models, measured over 24 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | GPT-5.6 SolQwen他测:v1.1 · 87 tasks · 每题3次均值;Opus/Fable=Claude Code,GPT=Codex,Qwen=OpenCode· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.5% |
| 2 | Claude Fable 5Qwen他测:v1.1 · 87 tasks · 每题3次均值;Opus/Fable=Claude Code,GPT=Codex,Qwen=OpenCode· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.9% |
| 3 | Qwen3.8 MaxQwen他测:v1.1 · 87 tasks · 每题3次均值;Opus/Fable=Claude Code,GPT=Codex,Qwen=OpenCode· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.2% |
| 4 | GPT 5.5OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 67.3% |
| 5 | GPT 5.5Codex · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 66.5% |
| 6 | Claude Opus 4.8Qwen他测:v1.1 · 87 tasks · 每题3次均值;Opus/Fable=Claude Code,GPT=Codex,Qwen=OpenCode· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.1% |
| 7 | Claude Opus 4.7Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 61.2% |
| 8 | Qwen3.7 MaxQwen他测:v1.1 · 87 tasks · 每题3次均值;Opus/Fable=Claude Code,GPT=Codex,Qwen=OpenCode· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.2% |
| 9 | Gemini 3.1 Pro PreviewGemini CLI · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 60.8% |
| 10 | GLM 5.1OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 58.4% |
| 11 | Hy3 (Deep Infra)Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 55.9% |
| 12 | Gemini 3 FlashGemini CLI · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 54.6% |
| 13 | Claude Opus 4.8OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 54.1% |
| 14 | Kimi K2.6OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 54% |
| 15 | Claude Opus 4.7OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 53.1% |
| 16 | MiniMax M3OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 53% |
| 17 | Gemini 3.1 Pro PreviewOpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 52.8% |
| 18 | GPT 5.2Codex · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 51.7% |
| 19 | Claude Opus 4.6Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 50.2% |
| 20 | Claude Opus 4.5Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 49% |
| 21 | Gemini 3.5 FlashOpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 48.2% |
| 22 | Claude Sonnet 4.6OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 47.2% |
| 23 | DeepSeek V4 FlashOpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 44.7% |
| 24 | GPT-5.4 miniOpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 41.4% |
| 25 | Claude Sonnet 4.5Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 36.2% |
| 26 | MiniMax M2.7OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 34.9% |
| 27 | Claude Haiku 4.5Claude Code · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 30.1% |
| 28 | Gemini 3.1 Flash LiteOpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 20.1% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| DeepSeek V4 Pro (version unspecified)OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 50.1% |
| Grok 4.3OpenHands · 87 tasks · 3 trials/task · max reasoning effort · with Skills· Reported by SkillsBench / BenchFlow· via BenchBoard docs | 41.7% |