List your company
ResearchFormerly WizWand

General Knowledge on GPQA Diamond (Acc)

76.7AccuracyGLM-4.7-Flash-T
25.32438.6625265.338Apr 3, 2026Apr 13, 2026Apr 23, 2026May 4, 2026May 14, 2026May 24, 2026Jun 4, 2026
Updated 4mo ago

Evaluation results

MethodLinks
GLM-4.7-Flash-T#Token=199002026.0476.7
JoyAI-LLM Flash#Token=28002026.0474.5
Qwen3.5-35B-A3B#Token=43002026.0474.2
Qwen3-Next-80B-A3B#Token=40002026.0473
Qwen3-30B-A3B#Token=41002026.0466.2
SDAR-8BScale=8B, Tokens=55B, FLOPs=2640, Decoding Strategy=greedy static decoding, Block Size=42026.0640.2
Fine-tunedBase LLM=Qwen-2.5-7B-Instruct, Parameters=x42026.0538.1
Fine-tunedBase LLM=Llama-3.1-8B-Instruct, Parameters=x42026.0537.7
DiDi-Merg.-LBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.02026.0537.4
DiDi-Merg.-LBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.02026.0537.2
FREE-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.082026.0537.2
Twin-MergingBase LLM=Qwen-2.5-7B-Instruct, Parameters=x2.252026.0536.8
Twin-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.252026.0536.1
OPDLM-8BScale=8B, Tokens=0.066B, FLOPs=4.2, Decoding Strategy=greedy static decoding, Block Size=42026.0636.1
FREE-MergingBase LLM=Llama-3.1-8B-Instruct, Parameters=x2.082026.0535.9
Zero-shotBase LLM=Qwen-2.5-7B-Instruct, Parameters=x12026.0534.7
Zero-shotBase LLM=Llama-3.1-8B-Instruct, Parameters=x12026.0533.6
SDAR-4BScale=4B, Tokens=55B, FLOPs=1320, Decoding Strategy=greedy static decoding, Block Size=42026.0633
Dream-7BScale=8B, Tokens=580B, FLOPs=24360, Decoding Strategy=greedy static decoding, Block Size=42026.0632.1
LLaDA-8BScale=8B, Tokens=1500B, FLOPs=72000, Decoding Strategy=greedy static decoding, Block Size=42026.0631.8
OPDLM-4BScale=4B, Tokens=0.076B, FLOPs=2.4, Decoding Strategy=greedy static decoding, Block Size=42026.0629.1
Fast-dLLM-v2-7BScale=8B, Tokens=1B, FLOPs=42, Decoding Strategy=greedy static decoding, Block Size=42026.0627.3