K2 Horizon 7B: benchmark results
Provider: Institute of Foundation Models. Released 2026-09-03. Access: Open.
Aggregate Rating 1623 ± 23, rank #636 of 2171 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Tau3 Banking | 27.63 | Success Rate (%) | 63.5 |
| LLM Stats (Tau3 Banking) | 25.8 | Score (%) | 63.2 |
| AA Humanity's Last Exam | 18.21 | Accuracy (%) | 63 |
| AA Long Context Reasoning | 69.67 | Accuracy (%) | 59.9 |
| AA GPQA Diamond | 75.25 | Accuracy (%) | 57.6 |
| LLM Stats Score | 25.74 | LLM Stats Score (conservative rating) | 54.5 |
| AA-Briefcase - Analytical Quality Elo | 1041.35 | Elo | 51 |
| AA-Briefcase - XLSX - Rubric Pass Rate | 27.27 | Rubric Pass Rate (%) | 47.3 |
| AA CritPt | 0.29 | Accuracy (%) | 45.9 |
| AA-Briefcase - PPTX - Rubric Pass Rate | 23.27 | Rubric Pass Rate (%) | 45.1 |
| AutomationBench-AA - Marketing - Raw Objective Completion | 53.9 | Raw Objective Completion (%) | 45.1 |
| AA GDPval | 1024.49 | ELO | 45 |
Interactive version: theaggregate.ai/model?slug=k2-horizon-7b · How It Works · Data refreshed daily, snapshot 2026-10-30.