- 作者
- DoDoT Data Lab
- Provider
- BazaarLink
- 交付方式
- 站内运行
每 10 分钟本地快照
模型智力监控
展示 DoDoT 定时保存的 BazaarLink 模型检测快照;手动刷新会重新采集并真实入库。这是来源方检测结果,不是 DoDoT 自建评测分数。
- 基准模型
- 60
- 总测试数
- 14.5万
- 24H 测试
- 1,296
- 24H 合格率
- 33.6%
最近 24 小时
仅展示最新合格率最高的 8 个模型合格率趋势
基于最近 141 个真实采集快照
anthropic/claude-sonnet-4.5DeepSeek V4 ProGPT-5.6 LunaDeepSeek V4.1 Flashanthropic/claude-haiku-5.5GPT-6 Solanthropic/claude-haiku-4.5anthropic/claude-fable-5.1
模型总测试数24H 测试(合格率)站点最后更新
GPT-6 Solopenai/gpt-6-sol
5,082
74(62.2%)
81
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash
5,129
102(69.6%)
335
Gemini 4 Carbongoogle/gemini-4-carbon
22
20(30.0%)
16
GPT-6 Astraopenai/gpt-6-astra
1.5万
172(28.5%)
446
anthropic/claude-haiku-5.5
369
16(62.5%)
75
anthropic/claude-opus-5.5
1.2万
261(42.9%)
796
GPT-6.1 Solopenai/gpt-6.1-sol
1万
177(4.5%)
729
GPT-6 Lunaopenai/gpt-6-luna
4,956
95(4.2%)
67
Gemini 4 Argongoogle/gemini-4-argon
870
48(27.1%)
146
anthropic/claude-fable-5.1
2,056
55(49.1%)
127
GPT-5.6 Solopenai/gpt-5.6-sol
3.2万
84(48.8%)
101
Gemini 3.8 Flashgoogle/gemini-3.8-flash
1,258
24(8.3%)
67
anthropic/claude-sonnet-5.5
1,832
44(40.9%)
186
GLM-5.3z-ai/glm-5.3
2,334
18(44.4%)
97
Claude Sonnet 5anthropic/claude-sonnet-5
2,560
2(0.0%)
38
Claude Fable 5anthropic/claude-fable-5
4,190
10(10.0%)
58
anthropic/claude-opus-4.8
5,597
4(25.0%)
32
Grok 4.5x-ai/grok-4.5
762
1(0.0%)
5
Kimi K3.1 Promoonshotai/kimi-k3.1-pro
71
12(0.0%)
21
Claude Opus 5anthropic/claude-opus-5
8,998
7(0.0%)
63
anthropic/claude-sonnet-4.6
1,189
5(0.0%)
20
anthropic/claude-haiku-4.5
641
8(50.0%)
9
anthropic/claude-opus-4.6
3,575
5(20.0%)
36
DeepSeek V4 Prodeepseek/deepseek-v4-pro
1,540
5(80.0%)
46
Kimi K3moonshotai/kimi-k3
1,071
4(0.0%)
33
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
483
10(0.0%)
8
GPT-5.6 Lunaopenai/gpt-5.6-luna
2,303
10(70.0%)
21
Grok 4.7x-ai/grok-4.7
659
8(12.5%)
47
DeepSeek V4 Flashdeepseek/deepseek-v4-flash
1,992
4(0.0%)
32
Gemini 2.5 Progoogle/gemini-2.5-pro
68
2(0.0%)
2
GPT-5.6 Terraopenai/gpt-5.6-terra
4,124
3(0.0%)
21
Gemini 3.6 Flashgoogle/gemini-3.6-flash
106
2(0.0%)
2
Gemini 3.7 Flashgoogle/gemini-3.7-flash
197
1(0.0%)
16
anthropic/claude-sonnet-4.5
95
1(100.0%)
4
DeepSeek V3.2deepseek/deepseek-v3.2
22
1(0.0%)
3
Gemini 2.5 Flashgoogle/gemini-2.5-flash
52
1(0.0%)
1
Grok 4.6x-ai/grok-4.6
647
0(尚无判定)
13
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite
34
0(尚无判定)
4
GLM-5.2z-ai/glm-5.2
1,097
0(尚无判定)
9
anthropic/claude-opus-4.7
1,811
0(尚无判定)
13
anthropic/claude-opus-4.5
117
0(尚无判定)
3
GPT-5.5openai/gpt-5.5
6,196
0(尚无判定)
3
GPT-5.4openai/gpt-5.4
860
0(尚无判定)
2
Grok 4.3x-ai/grok-4.3
25
0(尚无判定)
1
GPT-5.4 Miniopenai/gpt-5.4-mini
161
0(尚无判定)
1
GPT-5openai/gpt-5
22
0(尚无判定)
1
openai/gpt-4o
137
0(尚无判定)
1
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite
15
0(尚无判定)
1
GPT-5.3 Codexopenai/gpt-5.3-codex
74
0(尚无判定)
0
GLM-5z-ai/glm-5
37
0(尚无判定)
0
GLM-5.1z-ai/glm-5.1
172
0(尚无判定)
0
Kimi K2.6moonshotai/kimi-k2.6
46
0(尚无判定)
0
deepseek/deepseek-chat-v3.1
1
0(尚无判定)
0
GPT-4.1openai/gpt-4.1
3
0(尚无判定)
0
GPT-4.1 Miniopenai/gpt-4.1-mini
6
0(尚无判定)
0
Qwen 3 Next 80b A3b Instructqwen/qwen3-next-80b-a3b-instruct
1
0(尚无判定)
0
Qwen 3 Maxqwen/qwen3-max
3
0(尚无判定)
0
GPT-5 Miniopenai/gpt-5-mini
6
0(尚无判定)
0
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
23
0(尚无判定)
0
GPT-5.2openai/gpt-5.2
44
0(尚无判定)
0