Benchmark
PaperBench
Benchmark by OpenAI
Original paper v1
6.0 ± 0.3%
DeepSeek-R1 / BasicAgent
frontier lab
DeepSeek
Organization of DeepSeek-R1 in PaperBench's original Table 4.
frontier lab
Organization of DeepSeek-R1 in PaperBench's original Table 4.
Benchmark by OpenAI
Original paper v1
6.0 ± 0.3%
DeepSeek-R1 / BasicAgent