DeepSeek-R1-0528-Qwen3-8B Benchmark Details

DeepSeek-R1-0528-Qwen3-8B currently shows benchmark results led by AIME2025 (129 / 215, score 63.70), LiveCodeBench (163 / 250, score 51.30), GPQA Diamond (372 / 462, score 61.20).

Benchmark Results

DeepSeek-R1-0528-Qwen3-8B

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

HLE

Thinking Enabled

5.90

462 / 563

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Enabled

61.20

372 / 462

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Enabled

51.30

163 / 250

Math and Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Thinking Enabled

63.70

129 / 215

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Thinking Enabled

19.90

280 / 282

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench Hard

Thinking EnabledTools

1.50

237 / 244

Compare with other models