All AI models

All models2292Chat & Knowledge558Coding381Agents & Tool Use541Writing & Language360Vision & Documents395Image Generation & Editing183Video Generation148Speech & Voice358Embeddings & Retrieval671Decision models118Music & Sound29
ModelHumanity's Last ExamPer taskPriceSpeedSupportsContext
Claude Opus 5.5Anthropic
61.4max
$5.98$4 / $20961M
Claude Fable 5.1Anthropic
59.1max
$7.63$10 / $50691M
Gemini 4 ArgonGoogle
57.1high
$1.99$2 / $10841M
Claude Fable 5Anthropic
55.5max
$8.75$10 / $50671M
Claude Sonnet 5.5Anthropic
55max
$5.46$2 / $101371M
Claude Opus 5Anthropic
54.9max
$5.86$5 / $25551M
GPT-6 AstraOpenAI
54.7max
$3.26$10 / $50691.05M
Muse Wonder FullMeta
53.6
——1M
GPT-6.1 SolOpenAI
52.9max
$0.72$2 / $10521.05M
Muse WonderMeta
50.1max
$4.52$4 / $201611M
GPT-5.6 SolOpenAI
49.5max
$1.99$4 / $201141.05M
MiMo v2.6 ProXiaomiOpen
49.4thinking
$0.13$0.43 / $0.87541M
Muse Spark 1.3Meta
48.7max
$1.60$1.25 / $4.251281M
Claude Opus 4.8Anthropic
48.7max
$4.08$5 / $25661M
MiniMax M3.1 FlashMiniMax
48thinking
$0.22$0.15 / $0.601051M
GPT-6 SolOpenAI
47.9max
$1.04$2 / $101281.05M
Gemini 3.8 FlashGoogle
47.8high
$1.24$0.75 / $3.751491M
Gemini 3.1 Pro PreviewGoogle
47thinking
$1.30$2 / $121151M
Kimi K3Moonshot AIOpen
46.9max
$2.00$3 / $151121M
Step 5 PreviewStepFunOpen
46.5thinking
$1.03$1 / $2.70931M
Muse Spark 1.1Meta
46.2xhigh
$1.38$1.25 / $4.252801M
GPT-5.5OpenAI
45.8xhigh
$2.63$5 / $301131.05M
Muse Spark 1.2Meta
45.5xhigh
$0.97$1.25 / $4.253551M
Claude Haiku 5.5Anthropic
44.4max
$0.21$0.10 / $0.502341M
Grok 4.6xAI
44.1xhigh
$1.75$2 / $665500K
Muse Spark OpenMetaOpen
43.9xhigh
$0.84$1.25 / $4.251261M
GPT-5.4OpenAI
43.7xhigh
—$2.50 / $151271.05M
CJT-4.1 Flash 236B A21BChina Mobile
43.6thinking
——262K
DeepSeek V4.1 Flash 1017DeepSeekOpen
43.3max
$0.26$0.30 / $1.201671M
Grok 4.7xAI
43.1xhigh
$3.74$2 / $694500K
Qwen3.8 Max (0902)Alibaba (Qwen)
43.1thinking
$5.41$2 / $640984K
GPT-5.6 TerraOpenAI
42.9max
$1.40$2 / $121421.05M
Grok 4.5xAI
42.7high
$0.88$2 / $663500K
GPT-5.3 CodexOpenAI
42.5xhigh
—$1.75 / $14122400K
Qwen3.8 2.4T A95BAlibaba (Qwen)Open
42.4thinking
$2.16$2 / $6127262K
Claude Opus 4.7Anthropic
42.3max
—$5 / $25631M
GLM 5.3Z.aiOpen
42.3max
$2.01$1.40 / $4.401861M
Claude Sonnet 5Anthropic
41.3max
$5.09$2 / $10801M
GLM 5.2Z.aiOpen
41.1max
$1.47$1.40 / $4.401891M
DeepSeek V4 Pro 0813DeepSeekOpen
41max
$0.67$1.32 / $3.96901M
Gemini 3.6 FlashGoogle
40.8high
$1.60$0.75 / $3.752091M
Muse SparkMeta
40.7thinking
—$1.25 / $4.25—1M
Qwen3.7 MaxAlibaba (Qwen)
40.5thinking
$1.15$1.48 / $4.432011M
MMotif 3 (Beta)Motif Technologies
40.4
——262K
Claude Opus 4.6Anthropic
39.9max
—$5 / $25481M
GLM 5.3 FlashZ.aiOpen
39.9max
$0.28$0.15 / $0.501791M
GPT-5.6 LunaOpenAI
39.5max
$0.18$0.20 / $1.201781.05M
Ling 3.1 FlashinclusionAIOpen
39.4
$1.00$0.30 / $0.901451M
MiniMax M3MiniMaxOpen
39thinking
$0.51$0.30 / $1.20157524K
GPT-6 LunaOpenAI
38.5max
$0.068$0.10 / $0.501381.05M
Grok Build 0.1xAI
38.3thinking
—$1 / $266256K
Qwen3.8 FlashAlibaba (Qwen)Open
38thinking
$0.37$0.15 / $0.4755262K
GPT-5.2OpenAI
37.7xhigh
—$1.75 / $1495400K
Agnes 2.5 Pro BetaSapiens AI
37.5
—$0.10 / $0.301171M
Kimi K2.6Moonshot AIOpen
37.5thinking
$0.80$0.95 / $4109256K
Grok 4.3xAI
37.2high
$0.21$1.25 / $2.501881M
MMotif 3Motif TechnologiesOpen
37
—$0.50 / $2—262K
Gemini 3 Flash PreviewGoogle
36.6thinking
—$0.50 / $32111M
MiMo v2.5 ProXiaomiOpen
35.7thinking
$0.054$0.43 / $0.87461M
Qwen3.7 PlusAlibaba (Qwen)
35.6thinking
$0.22$0.32 / $1.28581M