ModelEnterpriseOps-Gym-AAPer taskPriceSpeedSupportsContext
51.1max
$8.75$10 / $50671M
49.6max
$0.67$1.32 / $3.96901M
48.3high
$1.48$2 / $665500K
Qwen3.8 Max (0902)Alibaba (Qwen)
47.6thinking
$5.41$2 / $640984K
Claude Opus 5Anthropic
47.5max
$5.86$5 / $25551M
Qwen3.8 2.4T A95BAlibaba (Qwen)Open
47.4thinking
$2.16$2 / $6127262K
47.3xhigh
$0.97$1.25 / $4.253551M
Step 5 PreviewStepFunOpen
47.2thinking
$1.03$1 / $2.70931M
GPT-5.5OpenAI
46.6xhigh
$2.63$5 / $301131.05M
Kimi K3Moonshot AIOpen
45.3max
$2.00$3 / $151121M
Qwen3.7 MaxAlibaba (Qwen)
45thinking
$1.15$1.48 / $4.432011M
44.7max
$5.09$2 / $10801M
Qwen3.8 27BAlibaba (Qwen)Open
44.2xhigh
$1.01$0.42 / $2.55114262K
44max
$4.08$5 / $25661M
42.9max
$1.99$4 / $201141.05M
GLM 5.2Z.aiOpen
42.7max
$1.47$1.40 / $4.401891M
TInkling SmallThinking MachinesOpen
42.7thinking
$0.089$0.45 / $1.20219256K
42.3high
$0.19$0.30 / $2.504541M
42.2thinking
$1.30$2 / $121151M
40.8max
$0.18$0.20 / $1.201781.05M
40.8high
$0.88$2 / $663500K
Qwen3.7 PlusAlibaba (Qwen)
40.6thinking
$0.22$0.32 / $1.28581M
Kimi K2.7 CodeMoonshot AIOpen
40.2thinking
$0.54$0.95 / $463256K
Kimi K2.6Moonshot AIOpen
38.5thinking
$0.80$0.95 / $4109256K
38.5max
$1.40$2 / $121421.05M
TInklingThinking MachinesOpen
38xhigh
—$0.95 / $4.05190256K
GLM 5.3Z.aiOpen
36.4max
$2.01$1.40 / $4.401861M
34.7high
$0.058$0.30 / $1.10141131K
34.6xhigh
$0.45$0.75 / $4.50307400K
33.7high
$0.50$1.50 / $7.50155262K
33.2max
$0.28$0.15 / $0.501791M
MiniMax M3MiniMaxOpen
32.1thinking
$0.51$0.30 / $1.20157524K
31.5xhigh
$0.18$0.20 / $1.25163400K
Qwen3.5 397B A17BAlibaba (Qwen)Open
30.9thinking
$0.47$0.60 / $3.6055262K
29.4thinking
$0.28$1 / $5105200K
Step 3.7 FlashStepFunOpen
29.1high
—$0.20 / $1.15123256K
28.9thinking
$0.58$0.50 / $2.501381M
Gemma 4 31BGoogleOpen
28.3thinking
—$0.10 / $0.3455256K
28high
$0.06$0.25 / $1.503661M
26.3high
$0.21$1.25 / $2.501881M
GPT OSS 120BOpenAIOpen
25.5high
$0.092$0.03 / $0.15243131K
23.5
$1.64$0.13 / $1.151481M
18.4thinking
$0.079$0.025 / $0.123431M