Benchmarks

综合能力

GDPval-AA v2

真实职场任务:能否交付可用的文档、表格、幻灯片和图示

它测什么

GDPval-AA v2 是 Artificial Analysis 基于 OpenAI GDPval 数据集进行的独立评测。它使用公开 gold 集中的 220 个任务,覆盖 9 个行业、44 种职业,要求模型提交实际工作成果,而不只是回答问题。

比如,官方示例会让模型给一支巡演乐队制作一页舞台布置 PDF:把歌手、鼓手、音箱和话筒放对位置,再列清楚输入、输出线路。能说出“舞台图应该怎么画”还不够,模型需要真正做出文件,内容和排版都要满足需求。

所有模型通过 Stirrup Agent 框架工作,可以使用命令行、文件处理、网页搜索与浏览等工具,每个任务最多执行 250 轮。评估时隐藏模型身份,把同一任务的两份成果交给从三模型评审团中抽取的 LLM 裁判比较,再将这些对比结果汇总成 Elo 评分。

怎么看分数

Elo 越高,表示交付成果在这套任务的两两比较中更受评审偏好;人类专家成果的基准设为 1,000 分。比如 A 得 1,500 分、B 得 1,200 分,只能说明 A 在这一评测中的相对表现更强,不表示 A 的正确率是 150%,也不表示效率高 25%。Elo 可以低于 0,表中的 ± 数值是官方公布的 95% 置信区间,分数接近时不要把名次差当成确定差距。本页保留 2026 年 9 月 17 日核对到的全部 247 条成绩和官方模型配置;标有 Fallback 的条目包含备用模型机制,不能当成单一模型独立完成的结果。榜单会随新增比较而变化,不能直接与 v1、模型发布时的旧快照或 OpenAI 自己公布的 GDPval 胜率混用;它也不是 AA Intelligence Index 的综合分。

来源Artificial Analysis

查看 GDPval-AA v2 官方评测方法

模型表现

核对于 247 条成绩

GDPval-AA v2 — 模型表现。选择列标题可排序。
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)AnthropicAgent · Stirrup
Stirrup1764± 19
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)AnthropicAgent · Stirrup
Stirrup1745± 19
Claude Opus 5 (Adaptive Reasoning, Max Effort)AnthropicAgent · Stirrup
Stirrup1735± 16
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)AnthropicAgent · Stirrup
Stirrup1708± 15
Muse Spark 1.3 (max)MetaAgent · Stirrup
Stirrup1703± 19
Qwen3.8 Max (0902)AlibabaAgent · Stirrup
Stirrup1689± 21
Grok 4.6 (xhigh)SpaceXAIAgent · Stirrup
Stirrup1663± 15
Muse Spark 1.3 (xhigh)MetaAgent · Stirrup
Stirrup1662± 19
GLM 5.3 FlashZ AIAgent · Stirrup
Stirrup1655± 15
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)AnthropicAgent · Stirrup
Stirrup1650± 18
Qwen3.8-Flash-NextAlibabaAgent · Stirrup
Stirrup1647± 17
Grok 4.6 (high)SpaceXAIAgent · Stirrup
Stirrup1643± 14
Grok 4.6 (medium)SpaceXAIAgent · Stirrup
Stirrup1643± 15
GLM-5.3 (max)Z AIAgent · Stirrup
Stirrup1642± 14
DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1632± 21
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)AnthropicAgent · Stirrup
Stirrup1631± 14
Qwen3.8 MaxAlibabaAgent · Stirrup
Stirrup1630± 14
Claude Opus 5 (Adaptive Reasoning, High Effort)AnthropicAgent · Stirrup
Stirrup1629± 15
Qwen3.8 2.4T A95BAlibabaAgent · Stirrup
Stirrup1628± 15
GPT-5.6 Sol (max)OpenAIAgent · Stirrup
Stirrup1624± 14
GPT-5.6 Sol (xhigh)OpenAIAgent · Stirrup
Stirrup1585± 14
GPT-6 Astra (max)OpenAIAgent · Stirrup
Stirrup1580± 20
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)AnthropicAgent · Stirrup
Stirrup1579± 18
DeepSeek V4 Flash 0731 Vision (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1577± 15
Agnes 3.0 FlashSapiens AIAgent · Stirrup
Stirrup1573± 22
GPT-6 Astra (xhigh)OpenAIAgent · Stirrup
Stirrup1555± 20
Kimi K3 (max)KimiAgent · Stirrup
Stirrup1548± 14
GPT-6 Astra (high)OpenAIAgent · Stirrup
Stirrup1530± 20
Claude Opus 5 (Adaptive Reasoning, Medium Effort)AnthropicAgent · Stirrup
Stirrup1525± 15
GPT-5.6 Sol (high)OpenAIAgent · Stirrup
Stirrup1524± 14
Muse Spark 1.2 (xhigh)MetaAgent · Stirrup
Stirrup1523± 15
Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)AnthropicAgent · Stirrup
Stirrup1504± 18
GPT-6 Astra (medium)OpenAIAgent · Stirrup
Stirrup1501± 20
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)AnthropicAgent · Stirrup
Stirrup1501± 14
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1493± 15
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)AnthropicAgent · Stirrup
Stirrup1489± 13
GPT-5.6 Terra (xhigh)OpenAIAgent · Stirrup
Stirrup1479± 14
GPT-5.6 Terra (max)OpenAIAgent · Stirrup
Stirrup1477± 14
Gemini 3.8 Flash (high)GoogleAgent · Stirrup
Stirrup1464± 19
Qwen3.8 27B (xhigh)AlibabaAgent · Stirrup
Stirrup1463± 16
Grok 4.6 (low)SpaceXAIAgent · Stirrup
Stirrup1461± 15
GPT-5.6 Luna (max)OpenAIAgent · Stirrup
Stirrup1460± 13
Gemini 3.8 Flash (medium)GoogleAgent · Stirrup
Stirrup1455± 19
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1442± 14
Gemini 3.7 Flash (high)GoogleAgent · Stirrup
Stirrup1433± 15
Qwen3.8 27B (medium)AlibabaAgent · Stirrup
Stirrup1430± 16
Grok 4.5 (high)SpaceXAIAgent · Stirrup
Stirrup1430± 15
GPT-5.6 Luna (xhigh)OpenAIAgent · Stirrup
Stirrup1428± 14
GPT-5.6 Sol (medium)OpenAIAgent · Stirrup
Stirrup1427± 13
GPT-6 Astra (low)OpenAIAgent · Stirrup
Stirrup1419± 20
GPT-5.6 Terra (high)OpenAIAgent · Stirrup
Stirrup1415± 14
Gemini 3.7 Flash (medium)GoogleAgent · Stirrup
Stirrup1407± 16
GLM-5.2 (max)Z AIAgent · Stirrup
Stirrup1406± 13
Qwen3.8 27B (low)AlibabaAgent · Stirrup
Stirrup1403± 16
Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)AnthropicAgent · Stirrup
Stirrup1401± 14
K2 Horizon 375B A23BMBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup1400± 19
GPT-5.5 (xhigh)OpenAIAgent · Stirrup
Stirrup1396± 13
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)AnthropicAgent · Stirrup
Stirrup1396± 14
Agnes 2.5 Pro BetaSapiens AIAgent · Stirrup
Stirrup1376± 17
GPT-5.6 Luna (high)OpenAIAgent · Stirrup
Stirrup1375± 14
Claude Opus 5 (Adaptive Reasoning, Low Effort)AnthropicAgent · Stirrup
Stirrup1372± 15
GPT-5.5 (high)OpenAIAgent · Stirrup
Stirrup1372± 13
Gemini 3.8 Flash (low)GoogleAgent · Stirrup
Stirrup1359± 16
GPT-5.6 Sol (low)OpenAIAgent · Stirrup
Stirrup1355± 14
Gemini 3.7 Flash (low)GoogleAgent · Stirrup
Stirrup1354± 16
Gemini 3.6 Flash (high)GoogleAgent · Stirrup
Stirrup1331± 15
GPT-5.6 Terra (medium)OpenAIAgent · Stirrup
Stirrup1318± 14
Claude Sonnet 5 (Adaptive Reasoning, High Effort)AnthropicAgent · Stirrup
Stirrup1308± 14
GPT-5.4 (xhigh)OpenAIAgent · Stirrup
Stirrup1307± 14
GLM-5.2 (Non-reasoning)Z AIAgent · Stirrup
Stirrup1306± 16
MiniMax-M3MiniMaxAgent · Stirrup
Stirrup1304± 14
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)AnthropicAgent · Stirrup
Stirrup1295± 14
Muse Spark 1.1 (xhigh)MetaAgent · Stirrup
Stirrup1294± 16
GPT-5.5 (medium)OpenAIAgent · Stirrup
Stirrup1288± 14
Claude Sonnet 5 (Non-reasoning, High Effort)AnthropicAgent · Stirrup
Stirrup1283± 15
GPT-5.6 Sol (Non-reasoning)OpenAIAgent · Stirrup
Stirrup1273± 14
Apodex 1.1ApodexAgent · Stirrup
Stirrup1273± 17
Gemini 3.5 Flash (high)GoogleAgent · Stirrup
Stirrup1259± 14
K2 Horizon MoVA 36B A4BMBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup1243± 21
Quasar 438B (max, based on GLM-5.2)Multiverse ComputingAgent · Stirrup
Stirrup1239± 19
Ling-3.0-flash-VLInclusionAIAgent · Stirrup
Stirrup1225± 21
DeepSeek V4 Pro 0424 (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1223± 14
Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)AnthropicAgent · Stirrup
Stirrup1223± 14
DeepSeek V4 Pro 0424 (Reasoning, High Effort)DeepSeekAgent · Stirrup
Stirrup1219± 17
Motif 3Motif TechnologiesAgent · Stirrup
Stirrup1199± 17
JT-4.1 Flash 236B A21BChina MobileAgent · Stirrup
Stirrup1193± 16
Inkling SmallThinking MachinesAgent · Stirrup
Stirrup1191± 17
Qwen3.7 MaxAlibabaAgent · Stirrup
Stirrup1190± 14
G9v3-39A5BAI9StarsAgent · Stirrup
Stirrup1189± 18
MiMo-V2.5-ProXiaomiAgent · Stirrup
Stirrup1186± 14
Kimi K3 (low)KimiAgent · Stirrup
Stirrup1185± 17
Motif 3 (Beta)Motif TechnologiesAgent · Stirrup
Stirrup1183± 17
GLM-5.1 (Reasoning)Z AIAgent · Stirrup
Stirrup1180± 14
GPT-5.6 Terra (low)OpenAIAgent · Stirrup
Stirrup1178± 15
Nex-N2-ProNex AGIAgent · Stirrup
Stirrup1175± 15
Solar Pro 4UpstageAgent · Stirrup
Stirrup1173± 16
Ling-3.0-flash-FinInclusionAIAgent · Stirrup
Stirrup1171± 21
GPT-5.6 Luna (medium)OpenAIAgent · Stirrup
Stirrup1169± 14
Inkling (xhigh)Thinking MachinesAgent · Stirrup
Stirrup1165± 17
GPT-5.6 Terra (Non-reasoning)OpenAIAgent · Stirrup
Stirrup1146± 14
Claude Sonnet 5 (Adaptive Reasoning, Low Effort)AnthropicAgent · Stirrup
Stirrup1145± 15
Grok Build 0.1 0616SpaceXAIAgent · Stirrup
Stirrup1138± 14
Hy3TencentAgent · Stirrup
Stirrup1136± 17
DeepSeek V4 Flash 0420 (Reasoning, Max Effort)DeepSeekAgent · Stirrup
Stirrup1116± 14
Kimi K2.7 CodeKimiAgent · Stirrup
Stirrup1114± 14
Qwen3.8 27B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup1113± 17
GPT-5.5 (low)OpenAIAgent · Stirrup
Stirrup1113± 15
Kimi K2.6KimiAgent · Stirrup
Stirrup1096± 13
GLM-4.7 (Reasoning)Z AIAgent · Stirrup
Stirrup1096± 16
GPT-5.4 mini (xhigh)OpenAIAgent · Stirrup
Stirrup1095± 14
K2 Horizon 7BMBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup1091± 21
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIAAgent · Stirrup
Stirrup1091± 14
Agnes 2.5 Pro AlphaSapiens AIAgent · Stirrup
Stirrup1088± 17
MiniMax-M2.7MiniMaxAgent · Stirrup
Stirrup1087± 14
DeepSeek V4 Flash 0420 (Reasoning, High Effort)DeepSeekAgent · Stirrup
Stirrup1083± 17
MiMo-V2.5XiaomiAgent · Stirrup
Stirrup1079± 17
Muse SparkMetaAgent · Stirrup
Stirrup1076± 14
GPT-5.6 Luna (low)OpenAIAgent · Stirrup
Stirrup1075± 15
Qwen3.6 27B (Reasoning)AlibabaAgent · Stirrup
Stirrup1069± 14
Qwen3.6 PlusAlibabaAgent · Stirrup
Stirrup1066± 14
Gemini 3.5 Flash-LiteGoogleAgent · Stirrup
Stirrup1063± 17
GPT-5.5 (Non-reasoning)OpenAIAgent · Stirrup
Stirrup1054± 14
Solar Open2 250BUpstageAgent · Stirrup
Stirrup1053± 18
A.X-K2SK TelecomAgent · Stirrup
Stirrup1044± 18
Qwen3.6 27B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup1043± 16
GPT-5.4 nano (xhigh)OpenAIAgent · Stirrup
Stirrup1035± 14
Grok 4.3 (Non-reasoning)SpaceXAIAgent · Stirrup
Stirrup1031± 14
Grok 4.3 (high)SpaceXAIAgent · Stirrup
Stirrup1018± 14
Ling 3.0 FlashInclusionAIAgent · Stirrup
Stirrup1017± 17
GPT-5 (high)OpenAIAgent · Stirrup
Stirrup1015± 16
Qwen3.6 35B A3B (Reasoning)AlibabaAgent · Stirrup
Stirrup991± 14
Claude 4.5 Sonnet (Reasoning)AnthropicAgent · Stirrup
Stirrup989± 16
GPT-5.6 Luna (Non-reasoning)OpenAIAgent · Stirrup
Stirrup987± 15
LongCat 2.0LongCatAgent · Stirrup
Stirrup965± 16
K2 Horizon 3.7BMBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup962± 21
Step 3.7 FlashStepFunAgent · Stirrup
Stirrup954± 14
Qwen3.6 35B A3B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup953± 18
Kimi K2.5 (Reasoning)KimiAgent · Stirrup
Stirrup936± 17
GPT-5.1 (high)OpenAIAgent · Stirrup
Stirrup930± 17
Qwen3.5 122B A10B (Reasoning)AlibabaAgent · Stirrup
Stirrup925± 15
K-EXAONE 2.0 0803LG AI ResearchAgent · Stirrup
Stirrup918± 19
Qwen3.5 397B A17B (Reasoning)AlibabaAgent · Stirrup
Stirrup905± 15
Gemini 3.1 Pro PreviewGoogleAgent · Stirrup
Stirrup904± 15
Muse Glimmer (high)MetaAgent · Stirrup
Stirrup893± 19
Qwen3.7 PlusAlibabaAgent · Stirrup
Stirrup886± 15
GPT-5 mini (high)OpenAIAgent · Stirrup
Stirrup880± 17
Mistral Medium 3.5MistralAgent · Stirrup
Stirrup875± 15
GLM-4.6 (Reasoning)Z AIAgent · Stirrup
Stirrup874± 17
Ring-2.6-1TInclusionAIAgent · Stirrup
Stirrup864± 15
Claude 4.5 Haiku (Reasoning)AnthropicAgent · Stirrup
Stirrup854± 15
KAT-Coder-Pro V1KwaiKATAgent · Stirrup
Stirrup845± 16
KAT Coder Pro V2KwaiKATAgent · Stirrup
Stirrup843± 18
Qwen3.5 122B A10B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup833± 18
MiniCPM5-2BOpenBMBAgent · Stirrup
Stirrup828± 22
DeepSeek V3.1 Terminus (Reasoning)DeepSeekAgent · Stirrup
Stirrup826± 18
Claude 4 Sonnet (Reasoning)AnthropicAgent · Stirrup
Stirrup819± 17
DeepSeek V3.2 (Reasoning)DeepSeekAgent · Stirrup
Stirrup810± 19
G9v3-3BAI9StarsAgent · Stirrup
Stirrup807± 26
MiMo-V2-Flash (Non-reasoning)XiaomiAgent · Stirrup
Stirrup788± 19
Nemotron 3.5 LightningNVIDIAAgent · Stirrup
Stirrup767± 19
Gemma 4 31B (Reasoning)GoogleAgent · Stirrup
Stirrup755± 16
gpt-oss-120b (high)OpenAIAgent · Stirrup
Stirrup745± 15
Qwen3.5 35B A3B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup740± 20
GPT-5.4 mini (Non-Reasoning)OpenAIAgent · Stirrup
Stirrup734± 16
Granite 4.2 30BIBMAgent · Stirrup
Stirrup721± 20
Ling 3.0 TinyInclusionAIAgent · Stirrup
Stirrup716± 20
Gemma 4 26B A4B (Reasoning)GoogleAgent · Stirrup
Stirrup693± 15
Gemma 4 31B (Non-reasoning)GoogleAgent · Stirrup
Stirrup691± 18
Devstral 2MistralAgent · Stirrup
Stirrup689± 17
GPT-5.4 nano (Non-Reasoning)OpenAIAgent · Stirrup
Stirrup681± 21
Devstral Small 2MistralAgent · Stirrup
Stirrup680± 16
Qwen3 Coder NextAlibabaAgent · Stirrup
Stirrup664± 18
GPT-5.5 Instant (June 2026)OpenAIAgent · Stirrup
Stirrup662± 17
Command A+CohereAgent · Stirrup
Stirrup658± 18
Mercury 2InceptionAgent · Stirrup
Stirrup646± 19
Granite 4.2 8BIBMAgent · Stirrup
Stirrup645± 21
Nemotron 3 Super 120B A12B (Reasoning)NVIDIAAgent · Stirrup
Stirrup644± 16
Nova 2.0 Pro Preview (medium)AmazonAgent · Stirrup
Stirrup630± 16
EXAONE 4.5 33BLG AI ResearchAgent · Stirrup
Stirrup628± 20
Gemini 2.5 ProGoogleAgent · Stirrup
Stirrup616± 17
HyperNova 60B 2605 (high, based on gpt-oss-120b)Multiverse ComputingAgent · Stirrup
Stirrup604± 19
Nova 2.0 Pro Preview (low)AmazonAgent · Stirrup
Stirrup601± 16
Gemini 3.1 Flash-LiteGoogleAgent · Stirrup
Stirrup596± 16
Gemma 4 12B (Reasoning)GoogleAgent · Stirrup
Stirrup591± 20
Qwen3.5 9B (Reasoning)AlibabaAgent · Stirrup
Stirrup588± 18
Mistral Large 3MistralAgent · Stirrup
Stirrup588± 16
Mistral Small 3.1MistralAgent · Stirrup
Stirrup550± 18
K-EXAONE (Reasoning)LG AI ResearchAgent · Stirrup
Stirrup540± 20
Mistral Small 4 (Reasoning)MistralAgent · Stirrup
Stirrup537± 19
Mistral Medium 3.1MistralAgent · Stirrup
Stirrup536± 17
Nova 2.0 Lite (high)AmazonAgent · Stirrup
Stirrup536± 17
gpt-oss-20b (high)OpenAIAgent · Stirrup
Stirrup514± 16
Trinity Large ThinkingArcee AIAgent · Stirrup
Stirrup512± 20
Nova 2.0 Pro Preview (Non-reasoning)AmazonAgent · Stirrup
Stirrup509± 16
DiffusionGemma 26B A4BGoogleAgent · Stirrup
Stirrup501± 17
Qwen3 235B A22B 2507 (Reasoning)AlibabaAgent · Stirrup
Stirrup495± 19
Ling 2.6 FlashInclusionAIAgent · Stirrup
Stirrup493± 19
Celeris-1CelerisAgent · Stirrup
Stirrup483± 21
DeepSeek R1 (Jan '25)DeepSeekAgent · Stirrup
Stirrup479± 18
North Mini CodeCohereAgent · Stirrup
Stirrup472± 18
GPT-4.1 miniOpenAIAgent · Stirrup
Stirrup453± 18
Nemotron Cascade 2 30B A3BNVIDIAAgent · Stirrup
Stirrup447± 21
Solar Pro 3UpstageAgent · Stirrup
Stirrup447± 16
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIAAgent · Stirrup
Stirrup438± 17
Ministral 3 14BMistralAgent · Stirrup
Stirrup432± 17
o3-mini (high)OpenAIAgent · Stirrup
Stirrup421± 19
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIAAgent · Stirrup
Stirrup416± 21
Claude 3.5 HaikuAnthropicAgent · Stirrup
Stirrup408± 18
Ministral 3 8BMistralAgent · Stirrup
Stirrup405± 17
Granite 4.2 3BIBMAgent · Stirrup
Stirrup390± 21
Granite 4.1 30BIBMAgent · Stirrup
Stirrup379± 16
gpt-oss-120b (low)OpenAIAgent · Stirrup
Stirrup364± 21
Magistral Medium 1.2MistralAgent · Stirrup
Stirrup362± 18
K2 Think V2MBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup328± 18
Qwen3 Next 80B A3B (Reasoning)AlibabaAgent · Stirrup
Stirrup325± 20
DeepSeek V3 0324DeepSeekAgent · Stirrup
Stirrup275± 19
Qwen3 30B A3B 2507 (Reasoning)AlibabaAgent · Stirrup
Stirrup274± 20
Qwen3 32B (Reasoning)AlibabaAgent · Stirrup
Stirrup240± 18
Ministral 3 3BMistralAgent · Stirrup
Stirrup234± 18
Magistral Small 1.2MistralAgent · Stirrup
Stirrup213± 19
LFM2.5-2.6BLiquid AIAgent · Stirrup
Stirrup202± 22
GPT-4OpenAIAgent · Stirrup
Stirrup189± 18
GPT-4o miniOpenAIAgent · Stirrup
Stirrup188± 19
Qwen3 14B (Reasoning)AlibabaAgent · Stirrup
Stirrup188± 19
DeepSeek V3 (Dec '24)DeepSeekAgent · Stirrup
Stirrup183± 19
Gemma 4 E4B (Reasoning)GoogleAgent · Stirrup
Stirrup177± 22
Qwen3.5 2B (Reasoning)AlibabaAgent · Stirrup
Stirrup166± 21
Qwen3 8B (Reasoning)AlibabaAgent · Stirrup
Stirrup165± 19
NVIDIA Nemotron 3 Nano 4BNVIDIAAgent · Stirrup
Stirrup159± 21
Granite 4.1 3BIBMAgent · Stirrup
Stirrup74± 20
Llama 4 ScoutMetaAgent · Stirrup
Stirrup60± 17
Llama 3.3 Instruct 70BMetaAgent · Stirrup
Stirrup50± 19
Gemma 4 E2B (Reasoning)GoogleAgent · Stirrup
Stirrup36± 21
Mistral Small 3.2MistralAgent · Stirrup
Stirrup29± 19
GPT-4.1 nanoOpenAIAgent · Stirrup
Stirrup13± 19
Llama 4 MaverickMetaAgent · Stirrup
Stirrup-45± 17
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIAAgent · Stirrup
Stirrup-122± 17
Qwen3.5 2B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup-130± 18
Qwen3.5 0.8B (Non-reasoning)AlibabaAgent · Stirrup
Stirrup-133± 18
MiniCPM-V 4.6 1.3BOpenBMBAgent · Stirrup
Stirrup-134± 17
Llama 3.1 Instruct 8BMetaAgent · Stirrup
Stirrup-151± 17
Qwen3.5 0.8B (Reasoning)AlibabaAgent · Stirrup
Stirrup-152± 17
Nanbeige4.1-3BNanbeigeAgent · Stirrup
Stirrup-166± 17
Gemma 3 12B InstructGoogleAgent · Stirrup
Stirrup-170± 17
Gemma 3 27B InstructGoogleAgent · Stirrup
Stirrup-171± 16
Phi-4 Mini InstructMicrosoftAgent · Stirrup
Stirrup-171± 17
K2 Horizon 0.9BMBZUAI Institute of Foundation ModelsAgent · Stirrup
Stirrup-174± 17

⌘K搜索知识库

最近收录

正在载入知识索引…