| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | River-LLM (Llama3.1 8B, τ=0.7) | – | Accuracy: 75.6 |
| common-sense-reasoning-on-arc-easy | River-LLM (Llama3.1 8B, τ=0.5) | – | Accuracy: 82.0 |
| math-word-problem-solving-on-math | River-LLM (Llama3.1 8B, τ=0.5) | – | Accuracy: 26.6 |
| question-answering-on-boolq | River-LLM (Llama3.1 8B, τ=0.5) | – | Accuracy: 83.4 |
| sentence-completion-on-hellaswag | River-LLM (Llama3.1 8B, τ=0.7) | – | Accuracy: 58.6 |