ModelVals LegalBenchPer taskPriceSpeedSupportsContext
88.6unstated
—$10 / $50—1M
88.5unstated
—$10 / $50—1M
88.3unstated
—$2 / $10—1M
87.4unstated
—$2 / $12—1M
87unstated
—$0.75 / $3.75—1M
Claude Opus 5Anthropic
87unstated
—$5 / $25—1M
87unstated
—$4 / $20—1.05M
86.9unstated
—$0.50 / $3—1M
86.7unstated
—$0.75 / $3.75—1M
GPT-5.5OpenAI
86.5unstated
—$5 / $30—1.05M
86.3unstated
—$2 / $6—500K
Kimi K3Moonshot AIOpen
86.2unstated
—$3 / $15—1M
GPT-5.4OpenAI
86xhigh
—$2.50 / $151271.05M
GPT-5OpenAI
86unstated
—$1.25 / $10—400K
86unstated
—$2 / $6—500K
GPT-5.1OpenAI
85.7unstated
—$1.25 / $10—400K
MiniMax M3MiniMaxOpen
85.4unstated
—$0.30 / $1.20—524K
85.3thinking
—$5 / $25—1M
85.3unstated
—$1.25 / $4.25—1M
85.3unstated
—$5 / $25—1M
85.1unstated
—$2 / $12—1.05M
Qwen 3.5 PlusAlibaba (Qwen)
85.1unstated
—$0.12 / $0.69—1M
85unstated
—$1.25 / $4.25—1M
Qwen3.7 MaxAlibaba (Qwen)
84.9max
—$1.48 / $4.43—1M
GLM 5.3Z.aiOpen
84.8unstated
—$1.40 / $4.40—1M
Kimi K2.6Moonshot AIOpen
84.7unstated
—$0.95 / $4—256K
84.6thinking
—$5 / $2558200K
84.5unstated
—$1.25 / $2.50—1M
84.4unstated
—$2 / $6—500K
GLM 5.1Z.aiOpen
84.4unstated
—$1.40 / $4.40—203K
Qwen 3.5 FlashAlibaba (Qwen)
84.3unstated
—$0.065 / $0.26—1M
Qwen3.6 PlusAlibaba (Qwen)
84.2unstated
—$0.50 / $3—1M
84.2unstated
—$1.25 / $4.25—1M
84.1thinking
$0.56$3 / $15521M
84.1unstated
—$0.30 / $2.50—1M
GLM 5.2Z.aiOpen
84.1unstated
—$1.40 / $4.40—1M
GLM 5Z.aiOpen
84.1unstated
—$1 / $3.20—203K
84unstated
—$0.20 / $1.20—1.05M
MiniMax M2.7MiniMaxOpen
84unstated
—$0.30 / $1.20—205K
83.9unstated
—$0.15 / $0.50—1M
83.9unstated
—$2 / $10—1M
o3OpenAI
83.8unstated
—$2 / $8—200K
Hy4 previewTencentOpen
83.8
—$0.83 / $2.50—1M
83.6unstated
—$5 / $25—1M
GLM 4.7Z.aiOpen
83.4unstated
—$0.60 / $2.20—203K
GPT-4.1OpenAI
83.1unstated
—$2 / $8—1M
Mercury 2.5inception
83.1unstated
—$0.20 / $0.75—260K
TInkling SmallThinking MachinesOpen
83unstated
—$0.45 / $1.20—256K
TInklingThinking MachinesOpen
83unstated
—$0.95 / $4.05—256K
GPT-5.2OpenAI
82.8unstated
—$1.75 / $14—400K
Qwen3.8 27BAlibaba (Qwen)Open
82.4unstated
—$0.42 / $2.55—262K
82.4unstated
—$1.32 / $3.96—1M
GPT-4oOpenAI
82.2unstated
—$2.50 / $10—128K
82.1unstated
—$3 / $15—1M
82.1unstated
—$0.50 / $2.50—1M
82thinking
—$0.10 / $0.404341M
Qwen3 MaxAlibaba (Qwen)
81.9max
—$1.20 / $6—262K
81.8unstated
—$0.25 / $2—400K
Kimi K2 0711Moonshot AIOpen
81.5unstated
—$0.50 / $2—128K
81.2thinking
$0.28$1 / $5105200K