Model
Intern-S2-Preview
A small-parameter preview language model in the Intern series, with approximately 36.1B parameters, notable for its performance on expert-knowledge benchmarks.
Timeline (last 90 days)
Oct 19
The top five in MMLU-Pro are separated by only 0.6 percentage points: Darwin-180B-RSI 88.1%, MiniMax-M2.1 88.0%, Intern-S2-Preview 88.0%, Qwen3.5-397B-A17B 87.8%, DeepSeek-V4-Pro 87.5%.
Unverified50%