K2 Horizon 0.9B: benchmark results
Provider: Institute of Foundation Models. Released 2026-09-03. Access: Open.
Aggregate Rating 1379 ± 24, rank #1559 of 2171 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 5.38 | Accuracy (%) | 31.4 |
| AA CritPt | 0 | Accuracy (%) | 20.9 |
| AA Terminal-Bench 4.0 | 0 | Pass@1 (%) | 15 |
| AA Long Context Reasoning | 6.33 | Accuracy (%) | 12.4 |
| LLM Stats Score | 0.48 | LLM Stats Score (conservative rating) | 12.1 |
| Tau3 Banking | 4.95 | Success Rate (%) | 9.6 |
| AA GDP.pdf - Construction - Criterion Pass Rate | 42.47 | Criterion Pass Rate (%) | 8.9 |
| AutomationBench-AA - Strict | 0 | Strict Task Success (%) | 7.4 |
| LLM Stats (AIME 2026) | 48.5 | Score (%) | 7.4 |
| AA-Briefcase - Analytical Quality Elo | 0 | Elo | 6.6 |
| AA GPQA Diamond | 29.29 | Accuracy (%) | 5.8 |
| AA GDP.pdf - Finance/Investing - Criterion Pass Rate | 28.15 | Criterion Pass Rate (%) | 5.1 |
Interactive version: theaggregate.ai/model?slug=k2-horizon-0-9b · How It Works · Data refreshed daily, snapshot 2026-10-30.