Language Understanding on MMLU-Pro (EM)
90.1Exact MatchGemini-3.0 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3.0 Protemperature=1, context window=128K2025.12 | 90.1 | |
| Claude-4.5-Sonnettemperature=1, context window=128K2025.12 | 88.2 | |
| GPT-5 Hightemperature=1, context window=128K2025.12 | 87.5 | |
| DeepSeek-V3.2thinking mode=true, temperature=1, context window=128K2025.12 | 85 | |
| Kimi-K2thinking mode=true, temperature=1, context window=128K2025.12 | 84.6 | |
| MiniMax M2temperature=1, context window=128K2025.12 | 82 | |
| MiMo-V2 FlashShots=5-shot, # Total Params=309B, # Active Params=15.1B2026.05 | 73.2 | |
| Nemotron-3-NanoShots=5-shot, # Total Params=31.6B, # Active Params=3.6B2026.05 | 65.1 | |
| Qwen3.5Shots=5-shot, # Total Params=35B, # Active Params=2.6B2026.05 | 62.5 | |
| LAGUNA XS.2Shots=5-shot, # Total Params=33.4B, # Active Params=3B2026.05 | 53 | |
| Gemma-4Shots=5-shot, # Total Params=25.2B, # Active Params=3.8B2026.05 | 47.5 |