Benchmark
Browser-use LinkedIn · 0.2.6
Scores are percentages.
Scores from Harbor Hub Leaderboards.
- Models measured
- 17
- Scores recorded
- 17
- Sources
- 1
- IQ weight
- 0.00
Score distribution
- 80.3%
- Mean
- 86.2%
- Median
- 17.6%
- Std dev
- 65.5%
- 10th percentile
- 98%
- 90th percentile
- 40.9%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 17 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Haiku 5.5v0-2-4· Harbor Hub Leaderboards | 98.7% |
| 2 | DeepSeek V4.1 Flashv0-2-4· Harbor Hub Leaderboards | 98.6% |
| 3 | Qwen3.8 Flashv0-2-4· Harbor Hub Leaderboards | 98% |
| 4 | GLM 5.3 Flashv0-2-4· Harbor Hub Leaderboards | 97.5% |
| 5 | DeepSeek V4 Prov0-2-4· Harbor Hub Leaderboards | 94.7% |
| 6 | GPT-6.1 Terrav0-2-4· Harbor Hub Leaderboards | 91.9% |
| 7 | GPT-6 Lunav0-2-4· Harbor Hub Leaderboards | 90.7% |
| 8 | Gemini 3.8 Flashv0-2-4· Harbor Hub Leaderboards | 86.2% |
| 9 | Gemini 4 Hydrogenv0-2-4· Harbor Hub Leaderboards | 86.2% |
| 10 | GPT-6.1 Solv0-2-4· Harbor Hub Leaderboards | 84.9% |
| 11 | GLM 5.3v0-2-4· Harbor Hub Leaderboards | 77.3% |
| 12 | Hy3 (Deep Infra)v0-2-4· Harbor Hub Leaderboards | 75.2% |
| 13 | Claude Sonnet 5.5v0-2-4· Harbor Hub Leaderboards | 68.5% |
| 14 | Gemini 3.5 Flash Litev0-2-4· Harbor Hub Leaderboards | 66.2% |
| 15 | Claude Opus 5.5v0-2-4· Harbor Hub Leaderboards | 65.5% |
| 16 | MiMo V2.6 Flashv0-2-4· Harbor Hub Leaderboards | 44.5% |
| 17 | Qwen3.8 Maxv0-2-4· Harbor Hub Leaderboards | 40.9% |