DeepSeek-R1-Distill-Llama-70B Benchmark Details

DeepSeek-R1-Distill-Llama-70B currently shows benchmark results led by MATH-500 (29 / 46, score 94.50), AIME2025 (152 / 216, score 53.70), GPQA Diamond (356 / 463, score 65.20).

Benchmark Results

DeepSeek-R1-Distill-Llama-70B

Benchmark Results

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

HLE

Thinking Enabled

5.10

480 / 565

Other

2 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

65.20

356 / 463

GPQA Diamond

Thinking Enabled

40.20

433 / 463

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

MATH-500

Standard Mode

94.50

29 / 46

AIME2025

Thinking Enabled

53.70

152 / 216

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Enabled

26.60

232 / 251

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Thinking EnabledTools

21.90

240 / 264

Terminal Bench Hard

Thinking EnabledTools

1.50

237 / 244

Instruction Following

1 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Thinking Enabled

27.60

272 / 282

Compare with other models