List your company
ResearchFormerly WizWand

Long-context Question Answering on FRAMES

73.54Avg@4 ScoreGPT5-Nano
40.57249.13157.6966.249Jan 18, 2026
Updated 8mo ago

Evaluation results

MethodLinks
GPT5-NanoBackbone=GPT5-Nano, Category=Frontier Models2026.0173.54
GPT-OSS-120BBackbone=GPT-OSS-120B, Category=Frontier Models2026.0172.69
LONGPASBackbone=Qwen3-30B-A3B-Thinking, Category=Reasoning Models, Training Strategy=LONGPAS2026.0171.84
Qwen3-30B-A3B-ThinkingBackbone=Qwen3-30B-A3B-Thinking, Category=Reasoning Models, Training Strategy=Vanilla2026.0169.66
RLVRBackbone=Qwen3-30B-A3B-Thinking, Category=Reasoning Models, Training Strategy=RLVR2026.0169.66
LONGPASBackbone=Qwen3-30B-A3B-Instruct, Category=Instruct Models, Training Strategy=LONGPAS2026.0168.93
RLVRBackbone=Qwen3-30B-A3B-Instruct, Category=Instruct Models, Training Strategy=RLVR2026.0166.26
Gemini-2.5-Flash-ThinkingBackbone=Gemini-2.5-Flash-Thinking, Category=Frontier Models2026.0165.78
LONGPASBackbone=Qwen3-4B-Instruct, Category=Instruct Models, Training Strategy=LONGPAS2026.0164.9
LONGPASBackbone=Qwen3-4B-Thinking, Category=Reasoning Models, Training Strategy=LONGPAS2026.0164.75
GPT-OSS-20BBackbone=GPT-OSS-20B, Category=Frontier Models2026.0164.44
Qwen3-30B-A3B-InstructBackbone=Qwen3-30B-A3B-Instruct, Category=Instruct Models, Training Strategy=Vanilla2026.0162.96
RLVRBackbone=Qwen3-4B-Thinking, Category=Reasoning Models, Training Strategy=RLVR2026.0162.74
RLVRBackbone=Qwen3-4B-Instruct, Category=Instruct Models, Training Strategy=RLVR2026.0160.92
Qwen3-4B-ThinkingBackbone=Qwen3-4B-Thinking, Category=Reasoning Models, Training Strategy=Vanilla2026.0160.84
LONGPASBackbone=LLaMA3.1-8B-Instruct, Category=Instruct Models, Training Strategy=LONGPAS2026.0160.62
RLVRBackbone=LLaMA3.1-8B-Instruct, Category=Instruct Models, Training Strategy=RLVR2026.0155.98
LONGPASBackbone=Qwen2.5-7B-Instruct, Category=Instruct Models, Training Strategy=LONGPAS2026.0155.76
RLVRBackbone=Qwen2.5-7B-Instruct, Category=Instruct Models, Training Strategy=RLVR2026.0150.97
Qwen3-4B-InstructBackbone=Qwen3-4B-Instruct, Category=Instruct Models, Training Strategy=Vanilla2026.0146.81
Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Category=Instruct Models, Training Strategy=Vanilla2026.0145.08
LLaMA3.1-8B-InstructBackbone=LLaMA3.1-8B-Instruct, Category=Instruct Models, Training Strategy=Vanilla2026.0141.84