List your company

Language Understanding on Multilingual MMLU internal translated version (Accuracy)

85.5AccuracyGPT-4o
45.25255.70166.1576.599Jul 31, 2024Oct 27, 2024Jan 24, 2025Apr 22, 2025Jul 20, 2025Oct 16, 2025Jan 13, 2026

Evaluation results

MethodLinks
GPT-4oshot=5-shot2024.0785.5
Llama 3 405Bshot=5-shot2024.0783.2
GPT-4shot=5-shot2024.0780.2
Llama 3 70Bshot=5-shot2024.0778.2
Qwen 3 14Bshots=5-Shot2026.0175.4
Ministral 3 14Bshots=5-Shot2026.0174.2
Ministral 3 8Bshots=5-Shot2026.0170.6
Qwen 3 8Bshots=5-Shot2026.0170
Gemma 3 12Bshots=5-Shot2026.0169
Qwen 3 4Bshots=5-Shot2026.0167.7
Ministral 3 3Bshots=5-Shot2026.0165.2
Mixtral 8×22Bshot=5-shot2024.0764.3
GPT-3.5 Turboshot=5-shot2024.0758.8
Llama 3 8Bshot=5-shot2024.0758.6
Gemma 3 4Bshots=5-Shot2026.0151.6
Mistral 7Bshot=5-shot2024.0746.8