Our new X account is live! Follow @wizwand_team for updates

Question Answering on ARC-e (test)

92.6Accuracy

LLaMA-2

Updated 4d ago

Evaluation Results

Method	Links
LLaMA-2 2023.10		92.6
LLaMA-2 2023.10		88.7
LLaMA-2 2023.10		86.3
LLaMA-2 2023.10		84.9
LLAMA-3.1-8B 2026.01		82.53
QWEN3-14B 2026.01		81.9
MISTRAL-7B 2026.01		81.73
LLaMA-2 2023.10		80.3
LLaMA-2 2023.10		80.1
DEEPSEEK-R1-QWEN-8B 2026.01		76.52
QWEN3-4B 2026.01		75.93
Pythia-6.9B w/ Qwen2-7B 2025.06		73.27
LLAMA-3.2-3B 2026.01		72.05
Pythia-6.9B w/ Qwen2-7B 2025.06		71.72
Pythia-6.9B w/ LLAMA3-8B 2025.06		69.78
Pythia-6.9B 2025.06		69.23
Pythia-6.9B w/ Gemma-7B 2025.06		68.94
Pythia-6.9B w/ Gemma-7B 2025.06		67.59
Pythia-6.9B w/ LLAMA3-8B 2025.06		67.05
DART 2026.01		66.71
Pythia-6.9B + Direct tuning 2025.06		66.25
Pythia-6.9B + Direct tuning 2025.06		66.2
DEEPSEEK-R1-LLAMA-8B 2026.01		66.2
Pythia-6.9B 2025.06		65.99
Pythia-6.9B + Sentence distill 2025.06		65.36
DART 2026.01		65.07
Pythia-1B w/ LLAMA3-8B 2025.06		64.56
Pythia-1B w/ LLAMA3-8B 2025.06		64.02
Pythia-1B w/ Qwen2-7B 2025.06		63.17
Pythia-1B w/ Qwen2-7B 2025.06		62.33
Pythia-6.9B + Sentence distill 2025.06		61.7
DART 2026.01		61.11
DART 2026.01		59.43
Pythia-1B 2025.06		58.71
Pythia-1B + Direct tuning 2025.06		57.49
Pythia-1B w/ Gemma-7B 2025.06		56.99
Pythia-1B 2025.06		56.82
Pythia-1B + Direct tuning 2025.06		55.64
DART 2026.01		55.43
Pythia-1B w/ Gemma-7B 2025.06		55.39
Pythia-1B + Sentence distill 2025.06		53.41
Pythia-1B + Sentence distill 2025.06		52.27
DART 2026.01		50.38
DART 2026.01		49.2