经济价值任务

GDPval-AA v2

GDPval-AA v2 公开评测榜单:覆盖真实职业任务和高经济价值知识工作。本站保留来源口径,不合成新的综合评分。

数据快照:2026-09-18T01:47:51.386Z查看原始来源 ↗
主要指标Leaderboard
快照日期2026-09-18T01:47:51.386Z
248 / 248 个模型
公开评测完整榜单
排名机构模型Elo95% CI发布日期
1AnthropicClaude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)1,745
裁判协议 v4.3.1
-19 / +19Sep 2026
2AnthropicClaude Opus 5 (Adaptive Reasoning, Max Effort)1,735
裁判协议 v4.3.1
-16 / +16Jul 2026
3AnthropicClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)1,724
裁判协议 v4.3.1
-16 / +16Sep 2026
4AnthropicClaude Opus 5 (Adaptive Reasoning, Xhigh Effort)1,708
裁判协议 v4.3.1
-15 / +15Jul 2026
5MetaMuse Spark 1.3 (max)1,703
裁判协议 v4.3.1
-19 / +19Sep 2026
6AlibabaQwen3.8 Max (0902)1,664
裁判协议 v4.3.1
-19 / +19Sep 2026
7SpaceXAIGrok 4.6 (xhigh)1,663
裁判协议 v4.3.1
-15 / +15Aug 2026
8MetaMuse Spark 1.3 (xhigh)1,662
裁判协议 v4.3.1
-19 / +19Sep 2026
9Z AIGLM 5.3 Flash1,655
裁判协议 v4.3.1
-15 / +15Aug 2026
10AnthropicClaude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)1,650
裁判协议 v4.3.1
-18 / +18Sep 2026
11AlibabaQwen3.8-Flash-Next1,647
裁判协议 v4.3.1
-17 / +17Aug 2026
12SpaceXAIGrok 4.6 (high)1,643
裁判协议 v4.3.1
-14 / +14Aug 2026
13SpaceXAIGrok 4.6 (medium)1,643
裁判协议 v4.3.1
-15 / +15Aug 2026
14Z AIGLM-5.3 (max)1,634
裁判协议 v4.3.1
-14 / +14Aug 2026
15DeepSeekDeepSeek V4.1 Flash (Reasoning, Max Effort)1,632
裁判协议 v4.3.1
-21 / +21Sep 2026
16AnthropicClaude Fable 51,631
裁判协议 v4.3.1
-14 / +14Jun 2026
17AlibabaQwen3.8 Max1,630
裁判协议 v4.3.1
-14 / +14Aug 2026
18AnthropicClaude Opus 5 (Adaptive Reasoning, High Effort)1,629
裁判协议 v4.3.1
-15 / +15Jul 2026
19AlibabaQwen3.8 2.4T A95B1,628
裁判协议 v4.3.1
-15 / +15Aug 2026
20OpenAIGPT-5.6 Sol (max)1,587
裁判协议 v4.3.1
-13 / +13Jul 2026
21OpenAIGPT-5.6 Sol (xhigh)1,585
裁判协议 v4.3.1
-14 / +14Jul 2026
22OpenAIGPT-6 Astra (max)1,580
裁判协议 v4.3.1
-20 / +20Sep 2026
23AnthropicClaude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)1,579
裁判协议 v4.3.1
-18 / +18Sep 2026
24DeepSeekDeepSeek V4 Flash Vision (Reasoning, Max Effort)1,577
裁判协议 v4.3.1
-15 / +15Aug 2026
25Sapiens AIAgnes 3.0 Flash1,573
裁判协议 v4.3.1
-22 / +22Sep 2026
26OpenAIGPT-6 Astra (xhigh)1,555
裁判协议 v4.3.1
-20 / +20Sep 2026
27KimiKimi K3 (max)1,548
裁判协议 v4.3.1
-14 / +14Jul 2026
28OpenAIGPT-6 Astra (high)1,530
裁判协议 v4.3.1
-20 / +20Sep 2026
29AnthropicClaude Opus 5 (Adaptive Reasoning, Medium Effort)1,525
裁判协议 v4.3.1
-15 / +15Jul 2026
30OpenAIGPT-5.6 Sol (high)1,524
裁判协议 v4.3.1
-14 / +14Jul 2026
31MetaMuse Spark 1.2 (xhigh)1,523
裁判协议 v4.3.1
-15 / +15Aug 2026
32AnthropicClaude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)1,504
裁判协议 v4.3.1
-18 / +18Sep 2026
33AnthropicClaude Sonnet 5 (Adaptive Reasoning, Max Effort)1,501
裁判协议 v4.3.1
-14 / +14Jun 2026
34OpenAIGPT-6 Astra (medium)1,501
裁判协议 v4.3.1
-20 / +20Sep 2026
35DeepSeekDeepSeek V4 Pro 0813 (Reasoning, Max Effort)1,493
裁判协议 v4.3.1
-15 / +15Aug 2026
36AnthropicClaude Opus 4.8 (Adaptive Reasoning, Max Effort)1,489
裁判协议 v4.3.1
-13 / +13May 2026
37OpenAIGPT-5.6 Terra (xhigh)1,479
裁判协议 v4.3.1
-14 / +14Jul 2026
38OpenAIGPT-5.6 Terra (max)1,477
裁判协议 v4.3.1
-14 / +14Jul 2026
39GoogleGemini 3.8 Flash (high)1,464
裁判协议 v4.3.1
-19 / +19Sep 2026
40AlibabaQwen3.8 27B (xhigh)1,463
裁判协议 v4.3.1
-16 / +16Aug 2026
41SpaceXAIGrok 4.6 (low)1,461
裁判协议 v4.3.1
-15 / +15Aug 2026
42OpenAIGPT-5.6 Luna (max)1,456
裁判协议 v4.3.1
-13 / +13Jul 2026
43GoogleGemini 3.8 Flash (medium)1,455
裁判协议 v4.3.1
-19 / +19Sep 2026
44DeepSeekDeepSeek V4 Flash 0731 (Reasoning, Max Effort)1,442
裁判协议 v4.3.1
-14 / +14Jul 2026
45GoogleGemini 3.7 Flash (high)1,433
裁判协议 v4.3.1
-15 / +15Aug 2026
46AlibabaQwen3.8 27B (medium)1,430
裁判协议 v4.3.1
-16 / +16Aug 2026
47SpaceXAIGrok 4.5 (high)1,430
裁判协议 v4.3.1
-15 / +15Jul 2026
48OpenAIGPT-5.6 Luna (xhigh)1,428
裁判协议 v4.3.1
-14 / +14Jul 2026
49OpenAIGPT-5.6 Sol (medium)1,427
裁判协议 v4.3.1
-13 / +13Jul 2026
50OpenAIGPT-6 Astra (low)1,419
裁判协议 v4.3.1
-20 / +20Sep 2026
51OpenAIGPT-5.6 Terra (high)1,415
裁判协议 v4.3.1
-14 / +14Jul 2026
52GoogleGemini 3.7 Flash (medium)1,407
裁判协议 v4.3.1
-16 / +16Aug 2026
53Z AIGLM-5.2 (max)1,406
裁判协议 v4.3.1
-13 / +13Jun 2026
54AlibabaQwen3.8 27B (low)1,403
裁判协议 v4.3.1
-16 / +16Aug 2026
55AnthropicClaude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)1,401
裁判协议 v4.3.1
-14 / +14Jun 2026
56Institute of Foundation ModelsK2 Horizon 375B A23B1,400
裁判协议 v4.3.1
-19 / +19Sep 2026
57OpenAIGPT-5.5 (xhigh)1,396
裁判协议 v4.3.1
-13 / +13Apr 2026
58AnthropicClaude Opus 4.7 (Adaptive Reasoning, Max Effort)1,396
裁判协议 v4.3.1
-14 / +14Apr 2026
59Sapiens AIAgnes 2.5 Pro Beta1,376
裁判协议 v4.3.1
-17 / +17Aug 2026
60OpenAIGPT-5.6 Luna (high)1,375
裁判协议 v4.3.1
-14 / +14Jul 2026
61AnthropicClaude Opus 5 (Adaptive Reasoning, Low Effort)1,372
裁判协议 v4.3.1
-15 / +15Jul 2026
62OpenAIGPT-5.5 (high)1,372
裁判协议 v4.3.1
-13 / +13Apr 2026
63GoogleGemini 3.8 Flash (low)1,359
裁判协议 v4.3.1
-16 / +16Sep 2026
64OpenAIGPT-5.6 Sol (low)1,355
裁判协议 v4.3.1
-14 / +14Jul 2026
65GoogleGemini 3.7 Flash (low)1,354
裁判协议 v4.3.1
-16 / +16Aug 2026
66GoogleGemini 3.6 Flash (high)1,331
裁判协议 v4.3.1
-15 / +15Jul 2026
67OpenAIGPT-5.6 Terra (medium)1,318
裁判协议 v4.3.1
-14 / +14Jul 2026
68AnthropicClaude Sonnet 5 (Adaptive Reasoning, High Effort)1,308
裁判协议 v4.3.1
-14 / +14Jun 2026
69OpenAIGPT-5.4 (xhigh)1,307
裁判协议 v4.3.1
-14 / +14Mar 2026
70Z AIGLM-5.2 (Non-reasoning)1,306
裁判协议 v4.3.1
-16 / +16Jun 2026
71MiniMaxMiniMax-M31,304
裁判协议 v4.3.1
-14 / +14Jun 2026
72AnthropicClaude Sonnet 4.6 (Adaptive Reasoning, Max Effort)1,295
裁判协议 v4.3.1
-14 / +14Feb 2026
73MetaMuse Spark 1.1 (xhigh)1,294
裁判协议 v4.3.1
-16 / +16Jul 2026
74OpenAIGPT-5.5 (medium)1,288
裁判协议 v4.3.1
-14 / +14Apr 2026
75AnthropicClaude Sonnet 5 (Non-reasoning, High Effort)1,283
裁判协议 v4.3.1
-15 / +15Jun 2026
76OpenAIGPT-5.6 Sol (Non-reasoning)1,273
裁判协议 v4.3.1
-14 / +14Jul 2026
77ApodexApodex 1.11,273
裁判协议 v4.3.1
-17 / +17Aug 2026
78GoogleGemini 3.5 Flash (high)1,259
裁判协议 v4.3.1
-14 / +14May 2026
79Institute of Foundation ModelsK2 Horizon MoVA 36B A4B1,243
裁判协议 v4.3.1
-21 / +21Sep 2026
80Multiverse ComputingQuasar 438B (max, based on GLM-5.2)1,239
裁判协议 v4.3.1
-19 / +19Aug 2026
81InclusionAILing-3.0-flash-VL1,225
裁判协议 v4.3.1
-21 / +21Sep 2026
82DeepSeekDeepSeek V4 Pro 0424 (Reasoning, Max Effort)1,223
裁判协议 v4.3.1
-14 / +14Apr 2026
83AnthropicClaude Sonnet 5 (Adaptive Reasoning, Medium Effort)1,223
裁判协议 v4.3.1
-14 / +14Jun 2026
84DeepSeekDeepSeek V4 Pro 0424 (Reasoning, High Effort)1,219
裁判协议 v4.3.1
-17 / +17Apr 2026
85Motif TechnologiesMotif 31,199
裁判协议 v4.3.1
-17 / +17Aug 2026
86China MobileJT-4.1 Flash 236B A21B1,193
裁判协议 v4.3.1
-16 / +16Jul 2026
87Thinking MachinesInkling Small1,191
裁判协议 v4.3.1
-17 / +17Jul 2026
88AlibabaQwen3.7 Max1,190
裁判协议 v4.3.1
-14 / +14May 2026
89AI9StarsG9v3-39A5B1,189
裁判协议 v4.3.1
-18 / +18Aug 2026
90XiaomiMiMo-V2.5-Pro1,186
裁判协议 v4.3.1
-14 / +14Apr 2026
91KimiKimi K3 (low)1,185
裁判协议 v4.3.1
-17 / +17Jul 2026
92Motif TechnologiesMotif 3 (Beta)1,183
裁判协议 v4.3.1
-17 / +17Jul 2026
93Z AIGLM-5.1 (Reasoning)1,180
裁判协议 v4.3.1
-14 / +14Apr 2026
94OpenAIGPT-5.6 Terra (low)1,178
裁判协议 v4.3.1
-15 / +15Jul 2026
95Nex AGINex-N2-Pro (based on Qwen3.5-397B-A17B)1,175
裁判协议 v4.3.1
-15 / +15Jun 2026
96UpstageSolar Pro 41,173
裁判协议 v4.3.1
-16 / +16Aug 2026
97InclusionAILing-3.0-flash-Fin1,171
裁判协议 v4.3.1
-21 / +21Sep 2026
98Thinking MachinesInkling (xhigh)1,165
裁判协议 v4.3.1
-17 / +17Jul 2026
99OpenAIGPT-5.6 Luna (medium)1,164
裁判协议 v4.3.1
-14 / +14Jul 2026
100OpenAIGPT-5.6 Terra (Non-reasoning)1,146
裁判协议 v4.3.1
-14 / +14Jul 2026
101AnthropicClaude Sonnet 5 (Adaptive Reasoning, Low Effort)1,145
裁判协议 v4.3.1
-15 / +15Jun 2026
102SpaceXAIGrok Build 0.1 06161,138
裁判协议 v4.3.1
-14 / +14Jun 2026
103TencentHy31,136
裁判协议 v4.3.1
-17 / +17Jul 2026
104DeepSeekDeepSeek V4 Flash 0420 (Reasoning, Max Effort)1,116
裁判协议 v4.3.1
-14 / +14Apr 2026
105KimiKimi K2.7 Code1,114
裁判协议 v4.3.1
-14 / +14Jun 2026
106AlibabaQwen3.8 27B (Non-reasoning)1,113
裁判协议 v4.3.1
-17 / +17Aug 2026
107OpenAIGPT-5.5 (low)1,113
裁判协议 v4.3.1
-15 / +15Apr 2026
108KimiKimi K2.61,096
裁判协议 v4.3.1
-13 / +13Apr 2026
109Z AIGLM-4.7 (Reasoning)1,096
裁判协议 v4.3.1
-16 / +16Dec 2025
110OpenAIGPT-5.4 mini (xhigh)1,095
裁判协议 v4.3.1
-14 / +14Mar 2026
111Institute of Foundation ModelsK2 Horizon 7B1,091
裁判协议 v4.3.1
-21 / +21Sep 2026
112NVIDIANemotron 3 Ultra 550B A55B (Reasoning)1,091
裁判协议 v4.3.1
-14 / +14Jun 2026
113Sapiens AIAgnes 2.5 Pro Alpha1,088
裁判协议 v4.3.1
-17 / +17Jul 2026
114MiniMaxMiniMax-M2.71,087
裁判协议 v4.3.1
-14 / +14Mar 2026
115DeepSeekDeepSeek V4 Flash 0420 (Reasoning, High Effort)1,083
裁判协议 v4.3.1
-17 / +17Apr 2026
116XiaomiMiMo-V2.51,079
裁判协议 v4.3.1
-17 / +17Apr 2026
117MetaMuse Spark1,076
裁判协议 v4.3.1
-14 / +14Apr 2026
118OpenAIGPT-5.6 Luna (low)1,075
裁判协议 v4.3.1
-15 / +15Jul 2026
119AlibabaQwen3.6 27B (Reasoning)1,069
裁判协议 v4.3.1
-14 / +14Apr 2026
120AlibabaQwen3.6 Plus1,066
裁判协议 v4.3.1
-14 / +14Apr 2026
121GoogleGemini 3.5 Flash-Lite1,063
裁判协议 v4.3.1
-17 / +17Jul 2026
122OpenAIGPT-5.5 (Non-reasoning)1,054
裁判协议 v4.3.1
-14 / +14Apr 2026
123UpstageSolar Open2 250B1,053
裁判协议 v4.3.1
-18 / +18Aug 2026
124SK TelecomA.X-K21,044
裁判协议 v4.3.1
-18 / +18Aug 2026
125AlibabaQwen3.6 27B (Non-reasoning)1,043
裁判协议 v4.3.1
-16 / +16Apr 2026
126OpenAIGPT-5.4 nano (xhigh)1,035
裁判协议 v4.3.1
-14 / +14Mar 2026
127SpaceXAIGrok 4.3 (Non-reasoning)1,031
裁判协议 v4.3.1
-14 / +14Apr 2026
128SpaceXAIGrok 4.3 (high)1,018
裁判协议 v4.3.1
-14 / +14Apr 2026
129InclusionAILing 3.0 Flash1,017
裁判协议 v4.3.1
-17 / +17Aug 2026
130OpenAIGPT-5 (high)1,015
裁判协议 v4.3.1
-16 / +16Aug 2025
131AlibabaQwen3.6 35B A3B (Reasoning)991
裁判协议 v4.3.1
-14 / +14Apr 2026
132AnthropicClaude 4.5 Sonnet (Reasoning)989
裁判协议 v4.3.1
-16 / +16Sep 2025
133OpenAIGPT-5.6 Luna (Non-reasoning)987
裁判协议 v4.3.1
-15 / +15Jul 2026
134LongCatLongCat 2.0965
裁判协议 v4.3.1
-16 / +16Jun 2026
135Institute of Foundation ModelsK2 Horizon 3.7B962
裁判协议 v4.3.1
-21 / +21Sep 2026
136StepFunStep 3.7 Flash954
裁判协议 v4.3.1
-14 / +14May 2026
137AlibabaQwen3.6 35B A3B (Non-reasoning)953
裁判协议 v4.3.1
-18 / +18Apr 2026
138KimiKimi K2.5 (Reasoning)936
裁判协议 v4.3.1
-17 / +17Jan 2026
139OpenAIGPT-5.1 (high)930
裁判协议 v4.3.1
-17 / +17Nov 2025
140AlibabaQwen3.5 122B A10B (Reasoning)925
裁判协议 v4.3.1
-15 / +15Feb 2026
141LG AI ResearchK-EXAONE 2.0 0803918
裁判协议 v4.3.1
-19 / +19Aug 2026
142AlibabaQwen3.5 397B A17B (Reasoning)905
裁判协议 v4.3.1
-15 / +15Feb 2026
143GoogleGemini 3.1 Pro Preview904
裁判协议 v4.3.1
-15 / +15Feb 2026
144MetaMuse Glimmer (high)893
裁判协议 v4.3.1
-19 / +19Aug 2026
145AlibabaQwen3.7 Plus886
裁判协议 v4.3.1
-15 / +15Jun 2026
146OpenAIGPT-5 mini (high)880
裁判协议 v4.3.1
-17 / +17Aug 2025
147MistralMistral Medium 3.5875
裁判协议 v4.3.1
-15 / +15Apr 2026
148Z AIGLM-4.6 (Reasoning)874
裁判协议 v4.3.1
-17 / +17Sep 2025
149InclusionAIRing-2.6-1T864
裁判协议 v4.3.1
-15 / +15May 2026
150AnthropicClaude 4.5 Haiku (Reasoning)854
裁判协议 v4.3.1
-15 / +15Oct 2025
151KwaiKATKAT-Coder-Pro V1845
裁判协议 v4.3.1
-16 / +16Nov 2025
152KwaiKATKAT Coder Pro V2843
裁判协议 v4.3.1
-18 / +18Mar 2026
153AlibabaQwen3.5 122B A10B (Non-reasoning)833
裁判协议 v4.3.1
-18 / +18Feb 2026
154OpenBMBMiniCPM5-2B828
裁判协议 v4.3.1
-22 / +22Sep 2026
155DeepSeekDeepSeek V3.1 Terminus (Reasoning)826
裁判协议 v4.3.1
-18 / +18Sep 2025
156AnthropicClaude 4 Sonnet (Reasoning)819
裁判协议 v4.3.1
-17 / +17May 2025
157DeepSeekDeepSeek V3.2 (Reasoning)810
裁判协议 v4.3.1
-19 / +19Dec 2025
158AI9StarsG9v3-3B807
裁判协议 v4.3.1
-26 / +26Jul 2026
159XiaomiMiMo-V2-Flash (Non-reasoning)788
裁判协议 v4.3.1
-19 / +19Dec 2025
160NVIDIANemotron 3.5 Lightning767
裁判协议 v4.3.1
-19 / +19Aug 2026
161GoogleGemma 4 31B (Reasoning)755
裁判协议 v4.3.1
-16 / +16Apr 2026
162OpenAIgpt-oss-120b (high)745
裁判协议 v4.3.1
-15 / +15Aug 2025
163AlibabaQwen3.5 35B A3B (Non-reasoning)740
裁判协议 v4.3.1
-20 / +20Feb 2026
164OpenAIGPT-5.4 mini (Non-Reasoning)734
裁判协议 v4.3.1
-16 / +16Mar 2026
165IBMGranite 4.2 30B721
裁判协议 v4.3.1
-20 / +20Aug 2026
166InclusionAILing 3.0 Tiny716
裁判协议 v4.3.1
-20 / +20Aug 2026
167GoogleGemma 4 26B A4B (Reasoning)693
裁判协议 v4.3.1
-15 / +15Apr 2026
168GoogleGemma 4 31B (Non-reasoning)691
裁判协议 v4.3.1
-18 / +18Apr 2026
169MistralDevstral 2689
裁判协议 v4.3.1
-17 / +17Dec 2025
170OpenAIGPT-5.4 nano (Non-Reasoning)681
裁判协议 v4.3.1
-21 / +21Mar 2026
171MistralDevstral Small 2680
裁判协议 v4.3.1
-16 / +16Dec 2025
172AlibabaQwen3 Coder Next664
裁判协议 v4.3.1
-18 / +18Feb 2026
173OpenAIGPT-5.5 Instant (June 2026)662
裁判协议 v4.3.1
-17 / +17Jun 2026
174CohereCommand A+658
裁判协议 v4.3.1
-18 / +18May 2026
175InceptionMercury 2646
裁判协议 v4.3.1
-19 / +19Feb 2026
176IBMGranite 4.2 8B645
裁判协议 v4.3.1
-21 / +21Aug 2026
177NVIDIANemotron 3 Super 120B A12B (Reasoning)644
裁判协议 v4.3.1
-16 / +16Mar 2026
178AmazonNova 2.0 Pro Preview (medium)630
裁判协议 v4.3.1
-16 / +16Nov 2025
179LG AI ResearchEXAONE 4.5 33B628
裁判协议 v4.3.1
-20 / +20Apr 2026
180GoogleGemini 2.5 Pro616
裁判协议 v4.3.1
-17 / +17Jun 2025
181Multiverse ComputingHyperNova 60B 2605 (high, based on gpt-oss-120b)604
裁判协议 v4.3.1
-19 / +19May 2026
182AmazonNova 2.0 Pro Preview (low)601
裁判协议 v4.3.1
-16 / +16Nov 2025
183GoogleGemini 3.1 Flash-Lite596
裁判协议 v4.3.1
-16 / +16Mar 2026
184GoogleGemma 4 12B (Reasoning)591
裁判协议 v4.3.1
-20 / +20Jun 2026
185AlibabaQwen3.5 9B (Reasoning)588
裁判协议 v4.3.1
-18 / +18Mar 2026
186MistralMistral Large 3588
裁判协议 v4.3.1
-16 / +16Dec 2025
187MistralMistral Small 3.1550
裁判协议 v4.3.1
-18 / +18Mar 2025
188LG AI ResearchK-EXAONE (Reasoning)540
裁判协议 v4.3.1
-20 / +20Dec 2025
189MistralMistral Small 4 (Reasoning)537
裁判协议 v4.3.1
-19 / +19Mar 2026
190MistralMistral Medium 3.1536
裁判协议 v4.3.1
-17 / +17Aug 2025
191AmazonNova 2.0 Lite (high)536
裁判协议 v4.3.1
-17 / +17Oct 2025
192OpenAIgpt-oss-20b (high)514
裁判协议 v4.3.1
-16 / +16Aug 2025
193Arcee AITrinity Large Thinking512
裁判协议 v4.3.1
-20 / +20Apr 2026
194AmazonNova 2.0 Pro Preview (Non-reasoning)509
裁判协议 v4.3.1
-16 / +16Nov 2025
195GoogleDiffusionGemma 26B A4B501
裁判协议 v4.3.1
-17 / +17Jun 2026
196AlibabaQwen3 235B A22B 2507 (Reasoning)495
裁判协议 v4.3.1
-19 / +19Jul 2025
197InclusionAILing 2.6 Flash493
裁判协议 v4.3.1
-19 / +19Apr 2026
198CelerisCeleris-1483
裁判协议 v4.3.1
-21 / +21Jul 2026
199DeepSeekDeepSeek R1 (Jan '25)479
裁判协议 v4.3.1
-18 / +18Jan 2025
200CohereNorth Mini Code472
裁判协议 v4.3.1
-18 / +18Jun 2026
201OpenAIGPT-4.1 mini453
裁判协议 v4.3.1
-18 / +18Apr 2025
202NVIDIANemotron Cascade 2 30B A3B447
裁判协议 v4.3.1
-21 / +21Mar 2026
203UpstageSolar Pro 3447
裁判协议 v4.3.1
-16 / +16Apr 2026
204NVIDIANVIDIA Nemotron 3 Nano 30B A3B (Reasoning)438
裁判协议 v4.3.1
-17 / +17Dec 2025
205MistralMinistral 3 14B432
裁判协议 v4.3.1
-17 / +17Dec 2025
206OpenAIo3-mini (high)421
裁判协议 v4.3.1
-19 / +19Jan 2025
207NVIDIANemotron 3 Nano Omni 30B A3B Reasoning416
裁判协议 v4.3.1
-21 / +21Apr 2026
208AnthropicClaude 3.5 Haiku408
裁判协议 v4.3.1
-18 / +18Oct 2024
209MistralMinistral 3 8B405
裁判协议 v4.3.1
-17 / +17Dec 2025
210IBMGranite 4.2 3B390
裁判协议 v4.3.1
-21 / +21Aug 2026
211IBMGranite 4.1 30B379
裁判协议 v4.3.1
-16 / +16Apr 2026
212OpenAIgpt-oss-120b (low)364
裁判协议 v4.3.1
-21 / +21Aug 2025
213MistralMagistral Medium 1.2362
裁判协议 v4.3.1
-18 / +18Sep 2025
214Institute of Foundation ModelsK2 Think V2328
裁判协议 v4.3.1
-18 / +18Dec 2025
215AlibabaQwen3 Next 80B A3B (Reasoning)325
裁判协议 v4.3.1
-20 / +20Sep 2025
216DeepSeekDeepSeek V3 0324275
裁判协议 v4.3.1
-19 / +19Mar 2025
217AlibabaQwen3 30B A3B 2507 (Reasoning)274
裁判协议 v4.3.1
-20 / +20Jul 2025
218AlibabaQwen3 32B (Reasoning)240
裁判协议 v4.3.1
-18 / +18Apr 2025
219MistralMinistral 3 3B234
裁判协议 v4.3.1
-18 / +18Dec 2025
220MistralMagistral Small 1.2213
裁判协议 v4.3.1
-19 / +19Sep 2025
221Liquid AILFM2.5-2.6B202
裁判协议 v4.3.1
-22 / +22Aug 2026
222OpenAIGPT-4189
裁判协议 v4.3.1
-18 / +18Mar 2023
223OpenAIGPT-4o mini188
裁判协议 v4.3.1
-19 / +19Jul 2024
224AlibabaQwen3 14B (Reasoning)188
裁判协议 v4.3.1
-19 / +19Apr 2025
225DeepSeekDeepSeek V3 (Dec '24)183
裁判协议 v4.3.1
-19 / +19Dec 2024
226GoogleGemma 4 E4B (Reasoning)177
裁判协议 v4.3.1
-22 / +22Apr 2026
227AlibabaQwen3.5 2B (Reasoning)166
裁判协议 v4.3.1
-21 / +21Mar 2026
228AlibabaQwen3 8B (Reasoning)165
裁判协议 v4.3.1
-19 / +19Apr 2025
229NVIDIANVIDIA Nemotron 3 Nano 4B159
裁判协议 v4.3.1
-21 / +21Mar 2026
230IBMGranite 4.1 3B74
裁判协议 v4.3.1
-20 / +20Apr 2026
231MetaLlama 4 Scout60
裁判协议 v4.3.1
-17 / +17Apr 2025
232MetaLlama 3.3 Instruct 70B50
裁判协议 v4.3.1
-19 / +19Dec 2024
233GoogleGemma 4 E2B (Reasoning)36
裁判协议 v4.3.1
-21 / +21Apr 2026
234MistralMistral Small 3.229
裁判协议 v4.3.1
-19 / +19Jun 2025
235OpenAIGPT-4.1 nano13
裁判协议 v4.3.1
-19 / +19Apr 2025
236MetaLlama 4 Maverick-45
裁判协议 v4.3.1
-17 / +17Apr 2025
237NVIDIANVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)-122
裁判协议 v4.3.1
-17 / +17Dec 2025
238AlibabaQwen3.5 2B (Non-reasoning)-130
裁判协议 v4.3.1
-18 / +18Mar 2026
239AlibabaQwen3.5 0.8B (Non-reasoning)-133
裁判协议 v4.3.1
-18 / +18Mar 2026
240OpenBMBMiniCPM-V 4.6 1.3B-134
裁判协议 v4.3.1
-17 / +17May 2026
241MetaLlama 3.1 Instruct 8B-151
裁判协议 v4.3.1
-17 / +17Jul 2024
242AlibabaQwen3.5 0.8B (Reasoning)-152
裁判协议 v4.3.1
-17 / +17Mar 2026
243NanbeigeNanbeige4.1-3B-166
裁判协议 v4.3.1
-17 / +17Feb 2026
244GoogleGemma 3 12B Instruct-170
裁判协议 v4.3.1
-17 / +17Mar 2025
245GoogleGemma 3 27B Instruct-171
裁判协议 v4.3.1
-16 / +16Mar 2025
246MicrosoftPhi-4 Mini Instruct-171
裁判协议 v4.3.1
-17 / +17Feb 2024
247Institute of Foundation ModelsK2 Horizon 0.9B-174
裁判协议 v4.3.1
-17 / +17Sep 2026
OpenAIGPT-6 Astra (Non-reasoning)
本轮来源未列出,保留上次观测
1,543
历史参考 2026-09-12
-20 / +20
历史参考 2026-09-12
Sep 2026

实时 Elo 的裁判协议与可比边界

AA-Briefcase 与 GDPval-AA v2 的当前成对比较使用裁判协议 v4.3.1,原评测名称与任务版本不变,Intelligence Index 仍为 v4.3。未区分裁判协议的旧 Elo 保留原始观测,仅作历史参考,不与当前协议混排。

指数中的 Elo 贡献在模型加入时冻结;实时榜单分数不能用于重算指数。来源未给出逐模型重跑日期,不能把裁判更新或跨协议分数差解释成新的模型运行或能力变化。

查看裁判、核验时间与完整方法边界 →查看 AA 原始方法 ↗

这个评测关注什么

覆盖真实职业任务和高经济价值知识工作。

阅读时注意

评测结果受任务集合、评分方法和模型版本影响。本站保留原始口径,不用它生成新的综合排名。

适用场景

用于回答一个明确的问题:模型在这一类任务上的相对表现如何,而不是“哪个模型绝对最好”。