BenchMark·Hub

Aider Polyglot

A已审核Benchmark
代码代码生成Aider 家族开放

发布方:Aider

热度8.0▲ 0.1

Aider Polyglot

aider / pass_rate_2 · 69 行结果

排名模型子项分数Metric时间
#1gpt-5 (high)
OpenAIaider --model openai/gpt-5
Aider Polyglot
aider
88%pass_rate_22025-08-23
#2gpt-5 (medium)
OpenAIaider --model openai/gpt-5
Aider Polyglot
aider
86.7%pass_rate_22025-08-25
#3o3-pro (high)
OpenAIaider --model o3-pro
Aider Polyglot
aider
84.9%pass_rate_22025-06-28
#4gemini-2.5-pro-preview-06-05 (32k think)
Googleaider --model gemini/gemini-2.5-pro-preview-06-05 --thinking-tokens 32k
Aider Polyglot
aider
83.1%pass_rate_22025-06-06
#5o3 (high)
OpenAIaider --model o3 --reasoning-effort high
Aider Polyglot
aider
81.3%pass_rate_22025-06-25
#6gpt-5 (low)
OpenAIaider --model openai/gpt-5
Aider Polyglot
aider
81.3%pass_rate_22025-08-25
#7grok-4 (high)
xAIaider --model openrouter/x-ai/grok-4
Aider Polyglot
aider
79.6%pass_rate_22025-07-11
#8gemini-2.5-pro-preview-06-05 (default think)
Googleaider --model gemini/gemini-2.5-pro-preview-06-05
Aider Polyglot
aider
79.1%pass_rate_22025-06-06
#9o3 (high) + gpt-4.1
OpenAIaider --model o3
Aider Polyglot
aider
78.2%pass_rate_22025-06-27
#10Gemini 2.5 Pro Preview 05-06
Googleaider --model gemini/gemini-2.5-pro-preview-05-06
Aider Polyglot
aider
76.9%pass_rate_22025-05-07
#11o3
OpenAIaider --model o3
Aider Polyglot
aider
76.9%pass_rate_22025-06-25
#12DeepSeek-V3.2-Exp (Reasoner)
DeepSeekaider --model deepseek/deepseek-reasoner
Aider Polyglot
aider
74.2%pass_rate_22025-10-03
#13Gemini 2.5 Pro Preview 03-25
Googleaider --model gemini/gemini-2.5-pro-preview-03-25
Aider Polyglot
aider
72.9%pass_rate_22025-04-12
#14o4-mini (high)
OpenAIaider --model o4-mini
Aider Polyglot
aider
72%pass_rate_22025-04-16
#15claude-opus-4-20250514 (32k thinking)
Anthropicaider --model claude-opus-4-20250514
Aider Polyglot
aider
72%pass_rate_22025-05-25
#16DeepSeek R1 (0528)
DeepSeekaider --model deepseek/deepseek-reasoner
Aider Polyglot
aider
71.4%pass_rate_22025-06-06
#17claude-opus-4-20250514 (no think)
Anthropicaider --model claude-opus-4-20250514
Aider Polyglot
aider
70.7%pass_rate_22025-05-25
#18DeepSeek-V3.2-Exp (Chat)
DeepSeekaider --model deepseek/deepseek-chat
Aider Polyglot
aider
70.2%pass_rate_22025-10-03
#19claude-3-7-sonnet-20250219 (32k thinking tokens)
Anthropicaider --model anthropic/claude-3-7-sonnet-20250219 --thinking-tokens 32k
Aider Polyglot
aider
64.9%pass_rate_22025-02-24
#20DeepSeek R1 + claude-3-5-sonnet-20241022
Anthropicaider --architect --model r1 --editor-model sonnet
Aider Polyglot
aider
64%pass_rate_22025-01-23
#21o1-2024-12-17 (high)
OpenAIaider --model openrouter/openai/o1
Aider Polyglot
aider
61.7%pass_rate_22024-12-21
#22claude-sonnet-4-20250514 (32k thinking)
Anthropicaider --model claude-sonnet-4-20250514
Aider Polyglot
aider
61.3%pass_rate_22025-05-24
#23o3-mini (high)
OpenAIaider --model o3-mini --reasoning-effort high
Aider Polyglot
aider
60.4%pass_rate_22025-01-31
#24claude-3-7-sonnet-20250219 (no thinking)
Anthropicaider --model sonnet
Aider Polyglot
aider
60.4%pass_rate_22025-02-24
#25Qwen3 235B A22B diff, no think, Alibaba API
Alibabaaider --model openai/qwen3-235b-a22b
Aider Polyglot
aider
59.6%pass_rate_22025-05-09
69 条结果 · 当前 1-25
1 / 3