AGIEval
A human-centric exam benchmark for general knowledge and reasoning reported in DeepSeek-V4 base-model evaluations.
1 models
Higher is better.
About this benchmark
- Metric
- Exact match
- Tasks
- General academic and professional exam questions
- Authors
- DeepSeek-AI (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.