ModelIFBenchPer taskPriceSpeedSupportsContext
83.3medium
—$1.25 / $2.50931M
MiniMax M3MiniMaxOpen
82.9thinking
$0.51$0.30 / $1.20157524K
81.4thinking
$0.58$0.50 / $2.501381M
Qwen3.7 MaxAlibaba (Qwen)
80.5thinking
$1.15$1.48 / $4.432011M
80.4
——1M
MiMo v2.5 ProXiaomiOpen
79.9thinking
$0.054$0.43 / $0.87461M
79.6low
—134256K
Qwen3.5 397B A17BAlibaba (Qwen)Open
78.8thinking
$0.47$0.60 / $3.6055262K
78thinking
—$0.50 / $32111M
Qwen3.7 PlusAlibaba (Qwen)
78thinking
$0.22$0.32 / $1.28581M
77.2high
$0.06$0.25 / $1.503661M
77.1thinking
$1.30$2 / $121151M
Qwen3.6 Max PreviewAlibaba (Qwen)
76.6thinking
—$1.30 / $7.80—262K
GLM 5.1Z.aiOpen
76.3thinking
$1.02$1.40 / $4.4072203K
Kimi K2.6Moonshot AIOpen
76thinking
$0.80$0.95 / $4109256K
75.9xhigh
$0.18$0.20 / $1.25163400K
75.9thinking
—$1.25 / $4.25—1M
GPT-5.5OpenAI
75.9xhigh
$2.63$5 / $301131.05M
MiniMax M2.7MiniMaxOpen
75.7thinking
—$0.30 / $1.2070205K
Qwen 3.5 122B A10BAlibaba (Qwen)Open
75.7thinking
$0.32$0.40 / $3.2082262K
Gemma 4 31BGoogleOpen
75.6thinking
—$0.10 / $0.3455256K
Qwen 3.5 27BAlibaba (Qwen)Open
75.6thinking
—$0.30 / $2.4062262K
75.4high
$0.053$0.25 / $2130400K
GPT-5.2OpenAI
75.4xhigh
—$1.75 / $1495400K
75.4xhigh
—$1.75 / $14122400K
Qwen3.6 PlusAlibaba (Qwen)
75.2thinking
—$0.50 / $3561M
Command A+CohereOpen
73.9thinking
—$0.30 / $1.50157128K
GPT-5.4OpenAI
73.9xhigh
—$2.50 / $151271.05M
Gemma 4 12BGoogleOpen
73.5thinking
—$0.10 / $0.30114256K
GLM 5.2Z.aiOpen
73.3max
$1.47$1.40 / $4.401891M
73.3xhigh
$0.45$0.75 / $4.50307400K
73.2thinking
—$1.20 / $4—203K
GPT-5OpenAI
73.1high
—$1.25 / $10102400K
GPT-5.1OpenAI
72.9high
—$1.25 / $10128400K
72.7max
$1.99$4 / $201141.05M
Qwen 3.5 35B A3BAlibaba (Qwen)Open
72.5thinking
—$0.25 / $281262K
Gemma 4 26B A4BGoogleOpen
72.4thinking
—$0.15 / $0.6055256K
MiniMax M2MiniMaxOpen
72.3thinking
—$0.30 / $1.20119205K
GLM 5Z.aiOpen
72.3thinking
—$1 / $3.2091203K
MiniMax M2.5MiniMaxOpen
71.6thinking
—$0.30 / $1.2071205K
71.5
——400K
71.5
$1.64$0.13 / $1.151481M
o3OpenAI
71.4thinking
—$2 / $8126200K
71.2max
$1.40$2 / $121421.05M
71.2high
$0.079$0.15 / $0.60151131K
71.1thinking
$0.017$0.06 / $0.24230131K
70.7high
—$0.30 / $2.501931M
Qwen3 Max ThinkingAlibaba (Qwen)
70.7thinking
—$1.20 / $6—256K
o1OpenAI
70.3thinking
—$15 / $60—200K
Kimi K2.5Moonshot AIOpen
70.2thinking
—$0.60 / $378256K
MiniMax M2.1MiniMaxOpen
69.9thinking
—$0.30 / $1.2072205K
Mercury 2inception
69.8high
$0.039$0.25 / $0.75487128K
69.1
——128K
GPT OSS 120BOpenAIOpen
69high
$0.092$0.03 / $0.15243131K
68.8thinking
—$0.43 / $0.87—1M
68.8high
$0.50$1.50 / $7.50155262K
68.4non-thinking
——256K
Kimi K2 ThinkingMoonshot AIOpen
68.1thinking
—$0.47 / $2169256K
GLM 4.7Z.aiOpen
67.9thinking
—$0.60 / $2.2061203K
67.6high
—$0.05 / $0.40185400K