Skip to main content

Leaderboard

Agentic leaderboard

How well a model plans multi-step work, calls tools, and carries a task to completion without a human steering every turn. A value the source did not publish stays unavailable rather than becoming a zero.

Agentic leaderboard

229 source-backed models, ranked by agentic score. Blended cost is the 75% input / 25% output mix used everywhere else on the site.

Models ranked by Agentic capability score
RankModelAgenticOverallBlended $/1M
1GPT-5.6 SolOpenAI · Proprietary93.680.46$8.00
2Kimi K3Moonshot AI · Pending9174.43$6.00
3Claude Fable 5Anthropic · Proprietary89.181.41$20.00
4GPT-5.6 TerraOpenAI · Proprietary87.971.13$4.50
5GPT-6 AstraOpenAI · Proprietary87.182.81$20.00
6Claude Opus 5Anthropic · Proprietary85.681.87$10.00
7Qwen3.8 MaxAlibaba · Open Weight83.673.17Unavailable
8Grok 4.6xAI · Proprietary83.669.74$3.00
9GLM-5.3Z.AI · Open WeightSelf-hosted83.666.93Unavailable
10Claude Sonnet 5Anthropic · Proprietary82.469.68$4.00
11Qwen3.8-27BAlibaba · Open WeightSelf-hosted82.464.29Unavailable
12Grok 4.5xAI · Proprietary81.767.99$3.00
13Muse Spark 1.2Meta · Proprietary81.470.28$2.00
14GPT-5.6 LunaOpenAI · Proprietary81.264.77$0.45
15GLM-5.3-FlashZ.AI · Open WeightSelf-hosted8166.06Unavailable
16GPT-5.5 ProOpenAI · Proprietary80.661.9$67.50
17Gemini 3.6 FlashGoogle · Proprietary80.268.42$3.00
18GPT-5.4 ProOpenAI · Proprietary79.360.49$67.50
19GLM-5.2Z.AI · Open Weight78.466.68$2.15
20GPT-5.5OpenAI · Proprietary77.271.86$11.25
21Mistral Medium 3.5 128BMistral · Open Weight76.842.56$3.00
22Claude Opus 4.8Anthropic · Proprietary76.672.17$10.00
23Muse Spark 1.1Meta · Proprietary75.970.18Unavailable
24Gemini 3.5 FlashGoogle · Proprietary75.368.02$3.38
25OAOrnith-1.5-397BOrnith AI · Open WeightSelf-hosted74.965.32Unavailable
26Gemini 3.8 FlashGoogle · Proprietary74.575.89$1.50
27GPT-5.4OpenAI · Proprietary7270.88$5.63
28Gemini 3.1 ProGoogle · Proprietary7270.14$4.50
29Kimi K2.7 CodeMoonshot AI · Open Weight7165.6$1.71
30DSdots3-note PreviewDots Studio · Open WeightSelf-hosted69.664.14Unavailable
31DeepSeek V4 Pro 0813DeepSeek · Proprietary67.363.69$0.54
32Grok 4.3xAI · Proprietary66.559.73$1.56
33Gemini 3.7 FlashGoogle · Proprietary65.768.52$1.50
34Claude Opus 4.7 (Adaptive)Anthropic · Proprietary64.769.31$10.00
35Qwen3.7 MaxAlibaba · Proprietary63.866.87Unavailable
36Claude Opus 4.6Anthropic · Proprietary63.569.21$10.00
37GPT-5.3 CodexOpenAI · Proprietary62.864.03$4.81
38Claude Fable 5.1Anthropic · Proprietary60.884.74$20.00
39Kimi K2.6Moonshot AI · Open Weight60.865.5$1.71
40MiMo-V2.5-ProXiaomi · Proprietary60.362.61Unavailable
41MiniMax M3MiniMax · Open Weight58.261.25$0.52
42Qwen3.7 PlusAlibaba · Proprietary58.161.6Unavailable
43TMInklingThinking Machines Lab · Open Weight57.660.38$2.57
44TMInkling-SmallThinking Machines Lab · Open Weight56.758.78$0.79
45MiMo-V2.5Xiaomi · Proprietary56.657.78Unavailable
46Qwen 3.6 Max (preview)Alibaba · Proprietary5663.94Unavailable
47GPT-5.4 miniOpenAI · Proprietary55.561.05$1.69
48Qwen3.6 PlusAlibaba · Proprietary52.560.36Unavailable
49Gemini 3.5 Flash-LiteGoogle · Proprietary51.858.78$0.85
50Ling 3.0 FlashInclusionAI · Open Weight51.646.83Unavailable
51Muse Glimmer 30BMeta · Open WeightSelf-hosted51.245.08$0.64
52Claude Sonnet 4.6Anthropic · Proprietary50.562.86$6.00
53Step 3.7 FlashStepFun · Open Weight50.449.78$0.44
54Claude Opus 4.5Anthropic · Proprietary47.358.42$10.00
55Qwen3.6-27BAlibaba · Open WeightSelf-hosted47.247.73Unavailable
56GLM-5.1Z.AI · Open Weight46.963.26$2.15
57Muse SparkMeta · Proprietary46.867.51Unavailable
58OAOrnith-1.5-35B-A3BOrnith AI · Open WeightSelf-hosted44.236.86Unavailable
59MiniMax M2.7MiniMax · Open Weight43.955.01$0.52
60GLM-5Z.AI · Open Weight42.861.47$1.55
61Qwen3.8-Flash-NextAlibaba · Open WeightSelf-hosted4156.98Unavailable
62Hy3 PreviewTencent · Open WeightSelf-hosted40.255.71$0.29
63Claude Opus 4.7Anthropic · Proprietary38.770.6$10.00
64Qwen3.6-35B-A3BAlibaba · Open Weight3643.85Unavailable
65Claude Sonnet 4.5Anthropic · Proprietary33.754.01$6.00
66Qwen3.5 397BAlibaba · Open Weight30.955.09$1.35
67Grok 4.20xAI · Proprietary29.767.27$3.00
68MAI-Thinking-1Microsoft · Proprietary28.150.84Unavailable
69Kimi K2.5 (Reasoning)Moonshot AI · Proprietary2857.39$1.20
70Kimi K2.5Moonshot AI · Open Weight2854.02$1.20
71Laguna M.1Poolside · Proprietary27.83.81Unavailable
72Nemotron 3 UltraNVIDIA · Open WeightSelf-hosted27.340.5Unavailable
73Qwen3.5-122B-A10BAlibaba · Open WeightSelf-hosted24.950.67Unavailable
74GPT-5.2OpenAI · Proprietary23.164.86$4.81
75Laguna XS.2Poolside · Open WeightSelf-hosted20.91.47Unavailable
76GPT-5.4 nanoOpenAI · Proprietary18.559.42$0.46
77Qwen3.5-27BAlibaba · Open WeightSelf-hosted15.555.14Unavailable
78Qwen3.5-35B-A3BAlibaba · Open WeightSelf-hosted13.753.47Unavailable
79GLM-4.7Z.AI · Open WeightSelf-hosted10.857.76Unavailable
80Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open WeightSelf-hosted10.820.46Unavailable
81GPT-5.2 ProOpenAI · ProprietaryUnavailable68.99$57.75
82Gemini 3 ProGoogle · ProprietaryUnavailable66.36$4.50
83GPT-5.1OpenAI · ProprietaryUnavailable63.18$3.44
84MiMo-V2-ProXiaomi · ProprietaryUnavailable62.51Unavailable
85Claude Opus 4.6 (Adaptive)Anthropic · ProprietaryUnavailable62.23Unavailable
86Gemini 3 FlashGoogle · ProprietaryUnavailable61.94$1.13
87GLM-5-TurboZ.AI · ProprietaryUnavailable61.42$1.90
88Hy4 previewTencent · Open WeightSelf-hostedUnavailable60.89$1.25
89Hy3Tencent · Open WeightSelf-hostedUnavailable60.79$0.14
90Gemini 3 Pro Deep ThinkGoogle · ProprietaryUnavailable59.32Unavailable
91Grok 4.1xAI · ProprietaryUnavailable57.99Unavailable
92GLM-5 (Reasoning)Z.AI · Open WeightUnavailable57.81$1.55
93Qwen3.5 397B (Reasoning)Alibaba · Open WeightUnavailable57.54$1.35
94MiMo-V2-OmniXiaomi · ProprietaryUnavailable57.53Unavailable
95GLM-5V-TurboZ.AI · ProprietaryUnavailable57.41$1.90
96Gemini 2.5 ProGoogle · ProprietaryUnavailable57.31$3.44
97GPT-5.2 InstantOpenAI · ProprietaryUnavailable57.05$2.63
98GPT-5.3 InstantOpenAI · ProprietaryUnavailable56.95$4.81
99DeepSeek V3.2DeepSeek · Open WeightUnavailable56.81$0.32
100GPT-5 (high)OpenAI · ProprietaryUnavailable56.7$3.44
101Gemini 3.1 Flash-LiteGoogle · ProprietaryUnavailable56.32$0.56
102DeepSeek V3.2 (Thinking)DeepSeek · Open WeightUnavailable56.19$0.96
103Qwen3.5 FlashAlibaba · ProprietaryUnavailable56.19$0.18
104Qwen3 235B 2507 (Reasoning)Alibaba · Open WeightSelf-hostedUnavailable56.08Unavailable
105GLM-4.5Z.AI · ProprietaryUnavailable55.64$1.00
106Gemma 4 26B A4BGoogle · Open WeightSelf-hostedUnavailable55Unavailable
107GPT-5.3-Codex-SparkOpenAI · ProprietaryUnavailable54.99Unavailable
108Grok 4.1 Fast (Reasoning)xAI · ProprietaryUnavailable54.82Unavailable
109MiniMax M2.5MiniMax · ProprietaryUnavailable54.76$0.52
110Qwen3 235B 2507Alibaba · Open WeightSelf-hostedUnavailable54.11Unavailable
111Trinity-Large-PreviewArcee AI · Open WeightUnavailable54.04$0.44
112GPT-5.2-CodexOpenAI · ProprietaryUnavailable53.95$4.81
113Grok 4xAI · ProprietaryUnavailable53.4Unavailable
114Claude Opus 4.5 ThinkingAnthropic · ProprietaryUnavailable53.05Unavailable
115Claude Haiku 4.5Anthropic · ProprietaryUnavailable52.89$2.00
116DeepSeek LLM 2.0DeepSeek · Open WeightSelf-hostedUnavailable52.65Unavailable
117GPT-5.1-Codex-MaxOpenAI · ProprietaryUnavailable52.6$3.44
118Gemma 4 31BGoogle · Open WeightSelf-hostedUnavailable52.4Unavailable
119Grok 3 [Beta]xAI · ProprietaryUnavailable51.85Unavailable
120APApodex 1.1Apodex · ProprietaryUnavailable51.74Unavailable
121GLM-4.6Z.AI · Open WeightUnavailable51.73Unavailable
122Gemini 2.5 FlashGoogle · ProprietaryUnavailable51.24$0.85
123Grok 4 Fast (Reasoning)xAI · ProprietaryUnavailable51.16Unavailable
124Nemotron 3 Nano 30BNVIDIA · Open WeightSelf-hostedUnavailable51.09Unavailable
125PMTernary Bonsai 2 27BPrism ML · Open WeightSelf-hostedUnavailable50.78$0.18
126DeepSeek V3.1DeepSeek · Open WeightSelf-hostedUnavailable50.72Unavailable
127DeepSeek-R1DeepSeek · Open WeightUnavailable50.55$0.96
128Qwen3.5 PlusAlibaba · ProprietaryUnavailable50.33$0.90
129Step 3.5 FlashStepFun · Open WeightUnavailable49.68$0.15
130GPT-5 (medium)OpenAI · ProprietaryUnavailable49.62Unavailable
131Qwen3.7 FlashAlibaba · ProprietaryUnavailable49.46$0.055
132Nemotron 3 Super 120B A12BNVIDIA · Open WeightSelf-hostedUnavailable49.15$0.17
133MiMo-V2-FlashXiaomi · Open WeightSelf-hostedUnavailable48.83Unavailable
134DeepSeek V3.1 (Reasoning)DeepSeek · Open WeightSelf-hostedUnavailable48.67Unavailable
135DeepSeek Coder 2.0DeepSeek · Open WeightUnavailable48.48Unavailable
136Seed 1.6ByteDance · ProprietaryUnavailable48.43Unavailable
137Nemotron 3 Super 100BNVIDIA · Open WeightSelf-hostedUnavailable48.28Unavailable
138o4-mini (high)OpenAI · ProprietaryUnavailable48.2$1.93
139GPT-5.1-CodexOpenAI · ProprietaryUnavailable48.16$3.44
140DeepSeekMath V2DeepSeek · Open WeightSelf-hostedUnavailable48.09Unavailable
141Qwen2.5-1MAlibaba · Open WeightSelf-hostedUnavailable48.09Unavailable
142Seed-2.0-LiteByteDance · ProprietaryUnavailable48.04Unavailable
143o3-proOpenAI · ProprietaryUnavailable47.84$35.00
144o3OpenAI · ProprietaryUnavailable47.58$3.50
145Ministral 3 14B (Reasoning)Mistral · Open WeightUnavailable47.56$0.20
146Grok 4.1 FastxAI · ProprietaryUnavailable47.14$0.28
147Grok 3 MinixAI · ProprietaryUnavailable46.98$0.35
148ALAion-2.0Aion Labs · ProprietaryUnavailable46.89$1.00
149o3-miniOpenAI · ProprietaryUnavailable46.72$1.93
150o1OpenAI · ProprietaryUnavailable46.19$26.25
151GLM-4.7-FlashZ.AI · Open WeightSelf-hostedUnavailable46.13Unavailable
152o1-previewOpenAI · ProprietaryUnavailable46.09$26.25
153GPT-OSS 120BOpenAI · Open WeightSelf-hostedUnavailable45.82$0.26
154Mistral Large 3Mistral · ProprietaryUnavailable45.45$0.75
155GPT-5 miniOpenAI · ProprietaryUnavailable45$0.69
156GLM-4.5-AirZ.AI · ProprietaryUnavailable43.73$0.43
157Z-1Z · ProprietaryUnavailable43.43Unavailable
158Seed 1.6 FlashByteDance · ProprietaryUnavailable43.39Unavailable
159Mistral 8x7BMistral · Open WeightSelf-hostedUnavailable43.29Unavailable
160Trinity-Large-ThinkingArcee AI · Open WeightUnavailable43.27$0.41
161Moonshot v1Moonshot AI · ProprietaryUnavailable43.1Unavailable
162Gemma 4 12BGoogle · Open WeightUnavailable42.99Unavailable
163Seed-2.0-MiniByteDance · ProprietaryUnavailable42.91Unavailable
164Command A+Cohere · Open WeightUnavailable42.85$4.38
165Mistral Small 4Mistral · Open WeightUnavailable42.85$0.26
166Nemotron Ultra 253BNVIDIA · Open WeightSelf-hostedUnavailable42.72Unavailable
167Mercury 2Inception · ProprietaryUnavailable42.17$0.38
168o1-proOpenAI · ProprietaryUnavailable42.05$262.50
169Claude 4.1 OpusAnthropic · ProprietaryUnavailable41.87$30.00
170DeepSeek V3DeepSeek · Open WeightUnavailable41.64$0.48
171GPT-4.1OpenAI · ProprietaryUnavailable41.29$3.50
172GPT-OSS 20BOpenAI · Open WeightSelf-hostedUnavailable41.08$0.055
173Nemotron 3 Nano Omni 30B A3BNVIDIA · Open WeightSelf-hostedUnavailable40.89Unavailable
174Qwen3 MaxAlibaba · ProprietaryUnavailable40.75$1.56
175Ling 2.6 FlashInclusionAI · Open WeightUnavailable40.59Unavailable
176Gemma 4 E4BGoogle · Open WeightSelf-hostedUnavailable40.18Unavailable
177SASarvam 105BSarvam · Open WeightSelf-hostedUnavailable40.12Unavailable
178LFM2.5-2.6BLiquidAI · Open WeightSelf-hostedUnavailable39.9Unavailable
179Gemma 4 E2BGoogle · Open WeightSelf-hostedUnavailable39.58Unavailable
180LFM2.5-8B-A1BLiquidAI · Open WeightSelf-hostedUnavailable39.28Unavailable
181Claude 4 SonnetAnthropic · ProprietaryUnavailable39.26$6.00
182SASarvam 30BSarvam · Open WeightSelf-hostedUnavailable38.93Unavailable
183GPT-4oOpenAI · ProprietaryUnavailable38.81$4.38
184Ministral 3 8B (Reasoning)Mistral · Open WeightUnavailable38.79$0.15
185Qwen3-Omni-30B-A3B-InstructAlibaba · Open WeightUnavailable38.64Unavailable
186Granite 4.2 8BIBM · Open WeightSelf-hostedUnavailable38.27Unavailable
187Qwen2.5-VL-32BAlibaba · Open WeightSelf-hostedUnavailable38.27Unavailable
188Llama 4 BehemothMeta · Open WeightSelf-hostedUnavailable38.22Unavailable
189Granite-4.0-H-1BIBM · Open WeightSelf-hostedUnavailable38.21Unavailable
190Granite-4.0-1BIBM · Open WeightSelf-hostedUnavailable38.06Unavailable
191Granite-4.0-350MIBM · Open WeightSelf-hostedUnavailable38.02Unavailable
192Granite-4.0-H-350MIBM · Open WeightSelf-hostedUnavailable38.02Unavailable
193Ministral 3 3B (Reasoning)Mistral · Open WeightUnavailable37.94$0.10
194Mistral 8x7B v0.2Mistral · Open WeightSelf-hostedUnavailable37.56Unavailable
195Qwen2.5-72BAlibaba · Open WeightSelf-hostedUnavailable37.52Unavailable
196GPT-5 nanoOpenAI · ProprietaryUnavailable36.91$0.14
197Llama 3.1 405BMeta · Open WeightSelf-hostedUnavailable36.7Unavailable
198Mistral Large 2Mistral · ProprietaryUnavailable36.33Unavailable
199Gemma 3 27BGoogle · Open WeightSelf-hostedUnavailable35.73Unavailable
200Claude 3 OpusAnthropic · ProprietaryUnavailable34.4$30.00
201Grok Code Fast 1xAI · ProprietaryUnavailable34.02$0.53
202Gemini 1.5 ProGoogle · ProprietaryUnavailable33.46$2.19
203GPT-4.1 miniOpenAI · ProprietaryUnavailable33.36$0.70
204Llama 4 ScoutMeta · Open WeightSelf-hostedUnavailable33.32$0.15
205Qwen2.5 Coder 32B InstructAlibaba · Open WeightSelf-hostedUnavailable33.3Unavailable
206GPT-4o miniOpenAI · ProprietaryUnavailable33.26$0.26
207Phi-4Microsoft · Open WeightSelf-hostedUnavailable33.09$0.0875
208DeepSeek R1 Distill Qwen 32BDeepSeek · Open WeightSelf-hostedUnavailable32.54Unavailable
209Claude 3.5 SonnetAnthropic · ProprietaryUnavailable32.09$6.00
210Claude 4.1 Opus ThinkingAnthropic · ProprietaryUnavailable31.4Unavailable
211Llama 3 70BMeta · Open WeightSelf-hostedUnavailable30.73Unavailable
212Mistral Medium 3Mistral · ProprietaryUnavailable30.64$0.80
213Ministral 3 14BMistral · Open WeightUnavailable30.19$0.20
214GPT-4.1 nanoOpenAI · ProprietaryUnavailable27.21$0.18
215Mixtral 8x22B Instruct v0.1Mistral · Open WeightSelf-hostedUnavailable26.85Unavailable
216GPT-4 TurboOpenAI · ProprietaryUnavailable24.4$15.00
217Kimi K2Moonshot AI · ProprietaryUnavailable23.12$1.08
218Llama 4 MaverickMeta · Open WeightSelf-hostedUnavailable22.73$0.30
219MiniMax M1 80kMiniMax · ProprietaryUnavailable21.38Unavailable
220Nova ProAmazon · ProprietaryUnavailable19.04Unavailable
221LFM2-24B-A2BLiquidAI · ProprietarySelf-hostedUnavailable18.48Unavailable
222Claude 3 HaikuAnthropic · ProprietaryUnavailable17.96$0.50
223Ministral 3 8BMistral · Open WeightUnavailable17.78$0.15
224LFM2.5-1.2B-ThinkingLiquidAI · ProprietarySelf-hostedUnavailable16.65Unavailable
225Gemini 1.0 ProGoogle · ProprietaryUnavailable16.32Unavailable
226LFM2.5-1.2B-InstructLiquidAI · ProprietarySelf-hostedUnavailable15.97Unavailable
227Ministral 3 3BMistral · Open WeightUnavailable15.96$0.10
228Nemotron-4 15BNVIDIA · Open WeightSelf-hostedUnavailable15.9Unavailable
229Mistral 7B v0.3Mistral · Open WeightSelf-hostedUnavailable8.66Unavailable

Evidence key: ObservedUnavailable

68 of these rows are marked self-hosted by the source: open-weight models with no first-party hosted token rate. 11 of them show a hosted rate matched from another provider; the rest report an unavailable price rather than zero.