List your company

Science Reasoning on GPQA Diamond (Metric: GPQA Diamond)

54.6GPQA DiamondQwen3-32B
-2.18412.55827.342.042May 14, 2026

Evaluation results

MethodLinks
Qwen3-32BTarget LLM=Public Models2026.0554.6
Qwen3-4BTarget LLM=Public Models2026.0541.7
DPA-Qwen3-32BTarget LLM=Qwen3-32B2026.0535.4
LLaVA-NeXT-Qwen3-32BTarget LLM=Qwen3-32B2026.0535.3
DPA-Qwen3-4BTarget LLM=Qwen3-4B2026.0533.3
LLaVA-NeXT-Qwen3-4BTarget LLM=Qwen3-4B2026.0532.8
DPA-LLaMA-3.2-3BTarget LLM=LLaMA-3.2-3B2026.0525.3
LLaVA-NeXT-LLaMA-3.2-3BTarget LLM=LLaMA-3.2-3B2026.0517.2
Qwen2-VL-2BTarget LLM=Public Models2026.0515.7
Idefics2-8BTarget LLM=Public Models2026.0515.2
LLaVA-1.5-7BTarget LLM=Public Models2026.0512.6
LLaVA-NeXT-7BTarget LLM=Public Models2026.0512.1
Cambrian-1-8BTarget LLM=Public Models2026.050