DataLearner logo

Kimi K2 Benchmark Details

Kimi K2 currently shows benchmark results led by Creative Writing (1 / 23, score 88.10), MMLU (12 / 65, score 89.50), MATH-500 (11 / 44, score 97.40).

Benchmark Results

Kimi K2

Benchmark Results

Thinking

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
MMLU
89.50
12 / 65
MMLU Pro
81.10
53 / 126
GPQA Diamond
75.10
94 / 179
LiveBench
Standard Mode
48.10
100 / 115
ARC-AGI
13.30
57 / 65
HLE
4.70
156 / 159

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
31
21 / 45

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
53.70
86 / 120
SWE-bench Verified
51.80
88 / 108

Math and Reasoning

7 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
97.40
11 / 44
AIME 2024
69.60
39 / 62
AIME2025
54
85 / 106
FrontierMath
2.10
47 / 60
IMO 2025
2
8 / 9
IMO 2024
0.50
10 / 10
FrontierMath - Tier 4
0.01
71 / 80

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
88.10
1 / 23

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
37.50
15 / 35

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Standard Mode
26.30
53 / 63

Agent Level Benchmark

4 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
65.80
28 / 35
τ²-Bench
64.30
27 / 40
τ²-Bench
64.30
27 / 40
Aider-Polyglot
Standard Mode
59.10
24 / 59
Compare with other models