Best for Agents & Tool Use

All models2292Chat & Knowledge558Coding381Agents & Tool Use541Writing & Language360Vision & Documents395Image Generation & Editing183Video Generation148Speech & Voice358Embeddings & Retrieval671Decision models118Music & Sound29
Modelτ²-benchPer taskPriceSpeedSupportsContext
GLM 5.2Z.aiOpen
99.1max
$1.47$1.40 / $4.401891M
CJT 35B FlashChina Mobile
99.1
——256K
GLM 4.7 FlashZ.aiOpen
98.8thinking
—$0.061 / $0.4075200K
Claude Fable 5Anthropic
98.5max
$8.75$10 / $50671M
Step 3.7 FlashStepFunOpen
98.5high
—$0.20 / $1.15123256K
GLM 5 TurboZ.ai
98.5thinking
—$1.20 / $4—203K
GLM 5V TurboZ.ai
98.5thinking
—$1.20 / $4—203K
GLM 5Z.aiOpen
98.2thinking
—$1 / $3.2091203K
Qwen3.6 PlusAlibaba (Qwen)
97.7thinking
—$0.50 / $3561M
Grok 4.3xAI
97.7high
$0.21$1.25 / $2.501881M
GLM 5.1Z.aiOpen
97.7thinking
$1.02$1.40 / $4.4072203K
Kimi K2.5Moonshot AIOpen
95.9thinking
—$0.60 / $378256K
Kimi K2.6Moonshot AIOpen
95.9thinking
$0.80$0.95 / $4109256K
GLM 4.7Z.aiOpen
95.9thinking
—$0.60 / $2.2061203K
Qwen3.6 Max PreviewAlibaba (Qwen)
95.9thinking
—$1.30 / $7.80—262K
Gemini 3.1 Pro PreviewGoogle
95.6thinking
$1.30$2 / $121151M
Qwen3.5 397B A17BAlibaba (Qwen)Open
95.6thinking
$0.47$0.60 / $3.6055262K
MiniMax M2.5MiniMaxOpen
95.3thinking
—$0.30 / $1.2071205K
Qwen3.6 35B A3BAlibaba (Qwen)Open
95.3thinking
$0.48$0.25 / $1.49138262K
MiMo v2 ProXiaomi
95thinking
—$0.43 / $0.87—1M
Qwen3.7 MaxAlibaba (Qwen)
94.7thinking
$1.15$1.48 / $4.432011M
Claude Opus 4.8Anthropic
94.4max
$4.08$5 / $25661M
Mistral Medium 3.5MistralOpen
94.2high
$0.50$1.50 / $7.50155262K
Qwen3.6 27BAlibaba (Qwen)Open
94.2thinking
$0.62$0.60 / $3.6059262K
MiMo v2.5 ProXiaomiOpen
94.2thinking
$0.054$0.43 / $0.87461M
GPT-5.5OpenAI
93.9xhigh
$2.63$5 / $301131.05M
Qwen 3.5 27BAlibaba (Qwen)Open
93.9thinking
—$0.30 / $2.4062262K
Qwen 3.5 122B A10BAlibaba (Qwen)Open
93.6thinking
$0.32$0.40 / $3.2082262K
TTri-21B-think PreviewTrillion LabsOpen
93.3
——32K
Kimi K2 ThinkingMoonshot AIOpen
93thinking
—$0.47 / $2169256K
Qwen3.7 PlusAlibaba (Qwen)
93thinking
$0.22$0.32 / $1.28581M
CJT MiniChina Mobile
93
——128K
Hy3 previewTencentOpen
92.7thinking
—$0.18 / $0.60—256K
Nova 2.0 Pro PreviewAmazon
92.7medium
—130256K
Ring 2.6 1TinclusionAIOpen
92.4
$0.29$0.13 / $1.10126128K
Claude Opus 4.6Anthropic
92.1max
—$5 / $25481M
Qwen3.5 4BAlibaba (Qwen)Open
92.1thinking
—$0.03 / $0.1518262K
Muse SparkMeta
91.5thinking
—$1.25 / $4.25—1M
MiMo v2 OmniXiaomi
91.2thinking
—$0.14 / $0.28—262K
MiMo v2.5XiaomiOpen
90.6thinking
$0.019$0.14 / $0.28381M
aTrinity Large Thinkingarcee-aiOpen
90.1thinking
$0.12$0.25 / $0.80362262K
Kimi K2.7 CodeMoonshot AIOpen
90.1thinking
$0.54$0.95 / $463256K
Ling 2.6 1TinclusionAIOpen
89.8
——262K
Claude Opus 4.5Anthropic
89.5thinking
—$5 / $2558200K
KKAT Coder Pro V2KwaiKAT
89.5
——256K
Qwen 3.5 35B A3BAlibaba (Qwen)Open
89.2thinking
—$0.25 / $281262K
MiniMax M3MiniMaxOpen
88.9thinking
$0.51$0.30 / $1.20157524K
Claude Opus 4.7Anthropic
88.6max
—$5 / $25631M
KKAT-Coder-Pro V1KwaiKAT
88.6non-thinking
——256K
MiMo v2 Omni 0327Xiaomi
88
——256K
OMiniCPM-V 4.6 1.3BOpenBMBOpen
87.7
——262K
nHyperCLOVA X SEED Think (32B)naverOpen
87.4
——128K
GPT-5.4OpenAI
87.1xhigh
—$2.50 / $151271.05M
MiniMax M2MiniMaxOpen
86.8thinking
—$0.30 / $1.20119205K
Qwen 3.5 9BAlibaba (Qwen)Open
86.8thinking
$0.21$0.08 / $0.1372262K
GPT-5OpenAI
86.5medium
—$1.25 / $10119400K
KMi:dm K 2.5 ProKorea Telecom
86.5
——128K
GPT-5.6 TerraOpenAI
86.3max
$1.40$2 / $121421.05M
Solar Pro 3Upstage
86.3high
$0.079$0.15 / $0.60151131K
GPT-5.3 CodexOpenAI
86xhigh
—$1.75 / $14122400K