List your company

General Knowledge Reasoning on MMLU-Pro

95.7AccuracyClaude Sonnet 4.5
48.026460.403272.7885.1568Nov 6, 2025Nov 20, 2025Dec 4, 2025Dec 18, 2025Jan 1, 2026Jan 15, 2026Jan 29, 2026

Evaluation results

MethodLinks
Claude Sonnet 4.5Input Modality=Text, LLM-as-a-Judge=GPT-4o2025.1195.7——
GPT-5 highInput Modality=Text, LLM-as-a-Judge=GPT-4o2025.1191.4——
Gemini 2.5 ProInput Modality=Text, LLM-as-a-Judge=GPT-4o2025.1187.1——
DeepSeek v3.22025.1284.6——
GLM-4.5Reported by AA Index=true2025.1283.5——
GLM-4.62025.1283.1——
INTELLECT-3Parameters=100B+2025.1281.9——
Sora-2 AudioInput Modality=Audio, LLM-as-a-Judge=GPT-4o2025.1176.5——
Std-PT.Backbone model=Deepseek-R1-Distill-Qwen-7B2026.0176.0211
T2Backbone model=Deepseek-R1-Distill-Qwen-7B2026.0175.840.230.49
ACBackbone model=Deepseek-R1-Distill-Qwen-7B2026.0175.720.472.32
ESCBackbone model=Deepseek-R1-Distill-Qwen-7B2026.0175.370.381.92
DeepSeek R1 05282025.1275.3——
GLM-4.5-Air2025.1273.9——
DeepConfBackbone model=Deepseek-R1-Distill-Qwen-7B2026.0173.40.593.88
T2Backbone model=Qwen3-4B2026.0172.20.220.4
DeepConfBackbone model=Qwen3-4B2026.0172.150.584.99
Sora-2 Last FrameInput Modality=Last Frame, LLM-as-a-Judge=GPT-4o2025.1172——
Std-PT.Backbone model=Qwen3-4B2026.0171.9811
ESCBackbone model=Qwen3-4B2026.0171.90.342.23
ACBackbone model=Qwen3-4B2026.0171.720.32.36
DSCBackbone model=Deepseek-R1-Distill-Qwen-7B2026.0171.140.351.79
DSCBackbone model=Qwen3-4B2026.0170.380.392.97
GPT-OSSParameters=120B2025.1267.1——
Std-PT.Backbone model=Qwen2.5-7B2026.0160.1811
T2Backbone model=Qwen2.5-7B2026.0160.10.230.39
DeepConfBackbone model=Qwen2.5-7B2026.0160.030.613.21
ACBackbone model=Qwen2.5-7B2026.0159.880.322.03
ESCBackbone model=Qwen2.5-7B2026.0159.880.281.78
DSCBackbone model=Qwen2.5-7B2026.0159.590.43.74
ESCBackbone model=Llama3.1-8B2026.0152.630.352.16
ACBackbone model=Llama3.1-8B2026.0152.580.313.17
Std-PT.Backbone model=Llama3.1-8B2026.0152.5411
T2Backbone model=Llama3.1-8B2026.0152.370.220.42
DSCBackbone model=Llama3.1-8B2026.01520.262.83
DeepConfBackbone model=Llama3.1-8B2026.0149.860.634.16