DataLearner logoDataLearnerAI
AI Tech Blogs
Leaderboards
Benchmarks
Models
Resources
Tool Directory

加载中...

DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

  • Leaderboards
  • 模型对比
  • Datasets

资源

  • Tutorials
  • Editorial
  • Tool directory

关于

  • 关于我们
  • 隐私政策
  • 数据收集方法
  • 联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款
Back to Main Leaderboard

大模型代码编程能力评测排行榜

本页面提供大模型代码编程能力评测排行榜，涵盖 SWE-Bench、LiveCodeBench、HumanEval 等数据集，对 GPT、Claude、Qwen、DeepSeek 等模型进行对比。

Updated on: 2025/10/12 20:54:51

Benchmark switcher

Pick the leaderboard to sync both chart and table

SWE-bench VerifiedLiveCodeBenchHumanEval

More benchmark coverage

Browse the benchmark catalog by category and language

More Benchmarks

Filters

Active
All3B and below7B13B34B65B100B and above
AllReasoning ModelsFoundation ModelsInstruction/Chat ModelsCoding Models

LLM Performance Results

Data source: DataLearnerAI
RankModelSWE-bench VerifiedLiveCodeBenchHumanEvalParams (B)License
1Kimi K2.576.8085.000.0010000BFree commercial
2Qwen3-Max-Thinking75.3085.900.0010000B不开源
3o3-pro75.000.000.00—不开源
4M2.174.800.000.002300BFree commercial
5Step 3.5 Flash74.4086.400.001960BFree commercial
6GLM-4.773.8084.900.003580BFree commercial
7DeepSeek V3.273.1083.300.006710BFree commercial
8Claude Opus 472.5056.600.00—不开源
9Kimi K2 Thinking71.3083.100.0010400BFree commercial
10Claude Sonnet 3.770.300.000.00—不开源
11MiniMax M269.4083.000.002300BFree commercial
12Kimi K2 090569.200.000.0010000BFree commercial
13DeepSeek-V3.1 Terminus68.4080.000.006710BFree commercial
14OpenAI o4 - mini68.100.000.00—不开源
15GLM-4.668.0084.500.003550BFree commercial
16DeepSeek V3.2-Exp67.8074.100.006710BFree commercial
17Qwen3-Coder-480B-A35B67.000.000.004800BFree commercial
18DeepSeek-V3.166.0074.800.006710BFree commercial
19GLM-4.564.2072.900.003550BFree commercial
20Gemini-2.5-Pro-Preview-05-0663.2077.100.00—不开源
21DeepSeek-R1-052857.6073.300.006710BFree commercial
22GLM-4.5-Air57.6070.700.001060BFree commercial
23MiniMax-M1-80k56.0065.000.004560BFree commercial
24MiniMax-M1-40k55.6062.300.004560BFree commercial
25GPT-4.154.6040.500.00—不开源
26Kimi K251.8053.700.0010000BFree commercial
27Gemini 2.5 Flash50.0055.400.00—不开源
28OpenAI o3-mini (high)49.3069.5097.60—不开源
29DeepSeek-R149.2065.900.006710BFree commercial
30OpenAI o148.9071.000.00—不开源
31DeepSeek-V3-032438.8049.200.006710BFree commercial
32GPT-4.538.0046.400.00—不开源
33Qwen3-235B-A22B34.4070.700.002350BFree commercial
34Gemini 2.5 Flash-Lite27.6034.300.00—不开源
35GPT-4.1 mini23.600.000.00—不开源
36Gemini 2.0 Flash Experimental21.4029.100.00—不开源
37Kimi-k1.6-IOI-high0.0073.800.00—不开源
38Step30.0067.100.003210BFree commercial
39Grok 30.0070.600.00—不开源
40OpenAI o3-mini (medium)0.0067.400.00—不开源
41Gemini 2.0 Flash-Lite0.0028.900.00—不开源
42Llama 4 Scout Instruct0.0032.800.001090BFree commercial
43ERNIE-4.5-300B-A47B0.0038.800.003000BFree commercial
44ERNIE-4.5-VL-424B-A47B-Base0.0038.800.004240BFree commercial
45Llama 4 Maverick Instruct0.0043.400.004000BFree commercial
46Llama 4 Behemoth Instruct0.0049.400.0020000BFree commercial
47Qwen3-235B-A22B-25070.0051.800.002350BFree commercial
48Magistral-Medium-25060.0059.360.00—不开源
49QwQ-Max-Preview0.0065.600.00—Free commercial
50Kimi-k1.6-IOI0.0065.900.00—不开源
51Qwen3-235B-A22B-Thinking-25070.0074.100.002350BFree commercial
52Grok-3 - Reasoning Beta0.0079.400.00—不开源
53Gemini 2.5 Pro Deep Think0.0080.400.00—不开源
54Qwen2.5-Max0.000.0073.20—不开源
55Grok-1.50.000.0074.10—不开源
56Codestral 25.010.0037.9086.60—不开源
57Grok 20.000.0088.402690BFree commercial
58DeepSeek-V30.0034.6089.006810BFree commercial
59Amazon Nova Pro0.000.0089.00—不开源
60Llama3.1-405B Instruct0.0030.2089.004050BFree commercial
61GPT-4o(2024-11-20)0.000.0090.20—不开源
62Hunyuan-TurboS0.0032.0091.00—不开源
63Claude 3.5 Sonnet0.000.0092.00—不开源
64OpenAI o1-mini0.0052.0092.40—不开源
1
Kimi K2.5
10000B
SWE-bench Verified76.80
LiveCodeBench85.00
HumanEval0.00
Free commercial
2
Qwen3-Max-Thinking
10000B
SWE-bench Verified75.30
LiveCodeBench85.90
HumanEval0.00
不开源
3
o3-pro
SWE-bench Verified75.00
LiveCodeBench0.00
HumanEval0.00
不开源
4
M2.1
2300B
SWE-bench Verified74.80
LiveCodeBench0.00
HumanEval0.00
Free commercial
5
Step 3.5 Flash
1960B
SWE-bench Verified74.40
LiveCodeBench86.40
HumanEval0.00
Free commercial
6
GLM-4.7
3580B
SWE-bench Verified73.80
LiveCodeBench84.90
HumanEval0.00
Free commercial
7
DeepSeek V3.2
6710B
SWE-bench Verified73.10
LiveCodeBench83.30
HumanEval0.00
Free commercial
8
Claude Opus 4
SWE-bench Verified72.50
LiveCodeBench56.60
HumanEval0.00
不开源
9
Kimi K2 Thinking
10400B
SWE-bench Verified71.30
LiveCodeBench83.10
HumanEval0.00
Free commercial
10
Claude Sonnet 3.7
SWE-bench Verified70.30
LiveCodeBench0.00
HumanEval0.00
不开源
11
MiniMax M2
2300B
SWE-bench Verified69.40
LiveCodeBench83.00
HumanEval0.00
Free commercial
12
Kimi K2 0905
10000B
SWE-bench Verified69.20
LiveCodeBench0.00
HumanEval0.00
Free commercial
13
DeepSeek-V3.1 Terminus
6710B
SWE-bench Verified68.40
LiveCodeBench80.00
HumanEval0.00
Free commercial
14
OpenAI o4 - mini
SWE-bench Verified68.10
LiveCodeBench0.00
HumanEval0.00
不开源
15
GLM-4.6
3550B
SWE-bench Verified68.00
LiveCodeBench84.50
HumanEval0.00
Free commercial
16
DeepSeek V3.2-Exp
6710B
SWE-bench Verified67.80
LiveCodeBench74.10
HumanEval0.00
Free commercial
17
Qwen3-Coder-480B-A35B
4800B
SWE-bench Verified67.00
LiveCodeBench0.00
HumanEval0.00
Free commercial
18
DeepSeek-V3.1
6710B
SWE-bench Verified66.00
LiveCodeBench74.80
HumanEval0.00
Free commercial
19
GLM-4.5
3550B
SWE-bench Verified64.20
LiveCodeBench72.90
HumanEval0.00
Free commercial
20
Gemini-2.5-Pro-Preview-05-06
SWE-bench Verified63.20
LiveCodeBench77.10
HumanEval0.00
不开源
21
DeepSeek-R1-0528
6710B
SWE-bench Verified57.60
LiveCodeBench73.30
HumanEval0.00
Free commercial
22
GLM-4.5-Air
1060B
SWE-bench Verified57.60
LiveCodeBench70.70
HumanEval0.00
Free commercial
23
MiniMax-M1-80k
4560B
SWE-bench Verified56.00
LiveCodeBench65.00
HumanEval0.00
Free commercial
24
MiniMax-M1-40k
4560B
SWE-bench Verified55.60
LiveCodeBench62.30
HumanEval0.00
Free commercial
25
GPT-4.1
SWE-bench Verified54.60
LiveCodeBench40.50
HumanEval0.00
不开源
26
Kimi K2
10000B
SWE-bench Verified51.80
LiveCodeBench53.70
HumanEval0.00
Free commercial
27
Gemini 2.5 Flash
SWE-bench Verified50.00
LiveCodeBench55.40
HumanEval0.00
不开源
28
OpenAI o3-mini (high)
SWE-bench Verified49.30
LiveCodeBench69.50
HumanEval97.60
不开源
29
DeepSeek-R1
6710B
SWE-bench Verified49.20
LiveCodeBench65.90
HumanEval0.00
Free commercial
30
OpenAI o1
SWE-bench Verified48.90
LiveCodeBench71.00
HumanEval0.00
不开源
31
DeepSeek-V3-0324
6710B
SWE-bench Verified38.80
LiveCodeBench49.20
HumanEval0.00
Free commercial
32
GPT-4.5
SWE-bench Verified38.00
LiveCodeBench46.40
HumanEval0.00
不开源
33
Qwen3-235B-A22B
2350B
SWE-bench Verified34.40
LiveCodeBench70.70
HumanEval0.00
Free commercial
34
Gemini 2.5 Flash-Lite
SWE-bench Verified27.60
LiveCodeBench34.30
HumanEval0.00
不开源
35
GPT-4.1 mini
SWE-bench Verified23.60
LiveCodeBench0.00
HumanEval0.00
不开源
36
Gemini 2.0 Flash Experimental
SWE-bench Verified21.40
LiveCodeBench29.10
HumanEval0.00
不开源
37
Kimi-k1.6-IOI-high
SWE-bench Verified0.00
LiveCodeBench73.80
HumanEval0.00
不开源
38
Step3
3210B
SWE-bench Verified0.00
LiveCodeBench67.10
HumanEval0.00
Free commercial
39
Grok 3
SWE-bench Verified0.00
LiveCodeBench70.60
HumanEval0.00
不开源
40
OpenAI o3-mini (medium)
SWE-bench Verified0.00
LiveCodeBench67.40
HumanEval0.00
不开源
41
Gemini 2.0 Flash-Lite
SWE-bench Verified0.00
LiveCodeBench28.90
HumanEval0.00
不开源
42
Llama 4 Scout Instruct
1090B
SWE-bench Verified0.00
LiveCodeBench32.80
HumanEval0.00
Free commercial
43
ERNIE-4.5-300B-A47B
3000B
SWE-bench Verified0.00
LiveCodeBench38.80
HumanEval0.00
Free commercial
44
ERNIE-4.5-VL-424B-A47B-Base
4240B
SWE-bench Verified0.00
LiveCodeBench38.80
HumanEval0.00
Free commercial
45
Llama 4 Maverick Instruct
4000B
SWE-bench Verified0.00
LiveCodeBench43.40
HumanEval0.00
Free commercial
46
Llama 4 Behemoth Instruct
20000B
SWE-bench Verified0.00
LiveCodeBench49.40
HumanEval0.00
Free commercial
47
Qwen3-235B-A22B-2507
2350B
SWE-bench Verified0.00
LiveCodeBench51.80
HumanEval0.00
Free commercial
48
Magistral-Medium-2506
SWE-bench Verified0.00
LiveCodeBench59.36
HumanEval0.00
不开源
49
QwQ-Max-Preview
SWE-bench Verified0.00
LiveCodeBench65.60
HumanEval0.00
Free commercial
50
Kimi-k1.6-IOI
SWE-bench Verified0.00
LiveCodeBench65.90
HumanEval0.00
不开源
51
Qwen3-235B-A22B-Thinking-2507
2350B
SWE-bench Verified0.00
LiveCodeBench74.10
HumanEval0.00
Free commercial
52
Grok-3 - Reasoning Beta
SWE-bench Verified0.00
LiveCodeBench79.40
HumanEval0.00
不开源
53
Gemini 2.5 Pro Deep Think
SWE-bench Verified0.00
LiveCodeBench80.40
HumanEval0.00
不开源
54
Qwen2.5-Max
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval73.20
不开源
55
Grok-1.5
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval74.10
不开源
56
Codestral 25.01
SWE-bench Verified0.00
LiveCodeBench37.90
HumanEval86.60
不开源
57
Grok 2
2690B
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval88.40
Free commercial
58
DeepSeek-V3
6810B
SWE-bench Verified0.00
LiveCodeBench34.60
HumanEval89.00
Free commercial
59
Amazon Nova Pro
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval89.00
不开源
60
Llama3.1-405B Instruct
4050B
SWE-bench Verified0.00
LiveCodeBench30.20
HumanEval89.00
Free commercial
61
GPT-4o(2024-11-20)
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval90.20
不开源
62
Hunyuan-TurboS
SWE-bench Verified0.00
LiveCodeBench32.00
HumanEval91.00
不开源
63
Claude 3.5 Sonnet
SWE-bench Verified0.00
LiveCodeBench0.00
HumanEval92.00
不开源
64
OpenAI o1-mini
SWE-bench Verified0.00
LiveCodeBench52.00
HumanEval92.40
不开源