DataLearner logo

DeepSeek-V3.1 Terminus Benchmark Details

DeepSeek-V3.1 Terminus currently shows benchmark results led by SimpleQA (2 / 47, score 96.80), MMLU Pro (26 / 132, score 85), LiveCodeBench (30 / 123, score 80).

Benchmark Results

DeepSeek-V3.1 Terminus

Benchmark Results

Thinking

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
85
26 / 132
MMLU Pro
85
26 / 132
GPQA Diamond
80.70
79 / 187
GPQA Diamond
79
87 / 187
HLE
21.70
108 / 170
HLE
15.20
132 / 170

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
96.80
2 / 47

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
80
30 / 123
LiveCodeBench
74.90
40 / 123
SWE-bench Verified
68.40
66 / 111

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
90
38 / 107
AIME2025
54
86 / 107

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
37
39 / 43
τ²-Bench
37
39 / 43
Compare with other models