AI Rankings

Explore the latest OpenClaw, Top Apps, and LLM rankings. Each section opens with the default view, and you can switch time ranges or views from the dropdown.

Rankings / Groups 11 / 3

Last updated Mar 26, 2026, 3:00 PM

OpenClaw

Benchmark rankings for OpenClaw task runs.

Score See which models score best on the OpenClaw task set.

Mar 21, 2026, 1:21 AM

Rank	Model	Score	Success rate	Submissions	Time	Best time	Lowest cost	Link
#1	Claude Opus 4.6 Anthropic	82.30%	87.45%	17	03/21, 08:44	1032.51s	$2.43	Link
#2	Mimo V2 Omni Xiaomi	81.82%	85.61%	6	03/21, 08:31	708.06s	$0.00	Link
#3	Minimax M2.7 Minimax	81.78%	87.13%	9	03/21, 08:41	1071.26s	$0.00	Link
#4	Gpt 5.4 Openai	81.57%	90.47%	15	03/21, 08:45	958.63s	$1.34	Link
#5	Glm 5 Turbo Z Ai	81.57%	86.54%	9	03/21, 08:50	984.42s	$0.00	Link
#6	Mimo V2 Pro Xiaomi	80.97%	83.95%	13	03/21, 09:07	904.74s	$0.00	Link
#7	Qwen3.5 122b A10b Qwen	80.80%	85.48%	13	03/19, 11:48	677.34s	$0.43	Link
#8	Claude Sonnet 4.5 Anthropic	80.67%	88.23%	17	03/21, 08:41	906.60s	$2.14	Link
#9	Claude Sonnet 4 Anthropic	80.47%	80.47%	1	03/10, 02:55	932.29s	$2.87	Link
#10	Qwen3.5 397b A17b Qwen	80.45%	89.14%	9	03/19, 12:03	885.84s	$0.75	Link

Claude Opus 4.6 Anthropic

Score 82.30%

Success rate 87.45% · Best time 1032.51s

Mimo V2 Omni Xiaomi

Score 81.82%

Success rate 85.61% · Best time 708.06s

Minimax M2.7 Minimax

Score 81.78%

Success rate 87.13% · Best time 1071.26s

Gpt 5.4 Openai

Score 81.57%

Success rate 90.47% · Best time 958.63s

Glm 5 Turbo Z Ai

Score 81.57%

Success rate 86.54% · Best time 984.42s

Mimo V2 Pro Xiaomi

Score 80.97%

Success rate 83.95% · Best time 904.74s

Qwen3.5 122b A10b Qwen

Score 80.80%

Success rate 85.48% · Best time 677.34s

Claude Sonnet 4.5 Anthropic

Score 80.67%

Success rate 88.23% · Best time 906.60s

Claude Sonnet 4 Anthropic

Score 80.47%

Success rate 80.47% · Best time 932.29s

#10

Qwen3.5 397b A17b Qwen

Score 80.45%

Success rate 89.14% · Best time 885.84s

Link

Speed See which models finish OpenClaw tasks the fastest.

Mar 21, 2026, 1:21 AM

Rank	Model	Best time	Success rate	Submissions	Time	Average time	Link
#1	Gpt Oss 20b Openai	345.05s	65.99%	11	03/21, 09:01	502.80s	Link
#2	Mercury 2 Inception	395.79s	78.01%	7	03/20, 08:59	503.44s	Link
#3	Deepseek V3.2 Deepseek	398.88s	84.30%	15	03/21, 09:18	2913.25s	Link
#4	Mimo V2 Flash Xiaomi	401.91s	81.51%	7	03/21, 08:34	1356.78s	Link
#5	Gpt 4o Openai	445.60s	71.14%	16	03/21, 08:25	601.26s	Link
#6	Gemini 3 Flash Preview Google	545.20s	85.22%	16	03/21, 08:32	784.84s	Link
#7	Gpt 5 Mini Openai	553.55s	80.29%	15	03/21, 08:26	860.93s	Link
#8	Gpt 4o Mini Openai	579.34s	75.05%	15	03/21, 08:33	975.02s	Link
#9	Gpt 5 Nano Openai	620.68s	68.78%	15	03/21, 08:28	745.92s	Link
#10	Qwen3.5 35b A3b Qwen	622.13s	78.35%	11	03/19, 02:29	894.58s	Link

Gpt Oss 20b Openai

Best time 345.05s

Average time 502.80s · Success rate 65.99%

Mercury 2 Inception

Best time 395.79s

Average time 503.44s · Success rate 78.01%

Deepseek V3.2 Deepseek

Best time 398.88s

Average time 2913.25s · Success rate 84.30%

Mimo V2 Flash Xiaomi

Best time 401.91s

Average time 1356.78s · Success rate 81.51%

Gpt 4o Openai

Best time 445.60s

Average time 601.26s · Success rate 71.14%

Gemini 3 Flash Preview Google

Best time 545.20s

Average time 784.84s · Success rate 85.22%

Gpt 5 Mini Openai

Best time 553.55s

Average time 860.93s · Success rate 80.29%

Gpt 4o Mini Openai

Best time 579.34s

Average time 975.02s · Success rate 75.05%

Gpt 5 Nano Openai

Best time 620.68s

Average time 745.92s · Success rate 68.78%

#10

Qwen3.5 35b A3b Qwen

Best time 622.13s

Average time 894.58s · Success rate 78.35%

Link

Cost See which models complete OpenClaw tasks at the lowest cost.

Mar 21, 2026, 1:21 AM

Rank	Model	Lowest cost	Success rate	Submissions	Time	Average cost	Link
#1	Gpt Oss 120b Openai	$0.03	60.61%	7	03/21, 08:22	$0.04	Link
#2	Qwen 2.5 7b Instruct Qwen	$0.06	40.29%	12	03/19, 11:57	$0.08	Link
#3	Qwen3.5 35b A3b Qwen	$0.07	78.35%	11	03/19, 02:29	$0.27	Link
#4	Mercury 2 Inception	$0.07	78.01%	7	03/20, 08:59	$0.11	Link
#5	Deepseek Chat Deepseek	$0.08	71.69%	16	03/21, 08:35	$0.19	Link
#6	Minimax M2.1 Minimax	$0.11	84.27%	21	03/21, 08:46	$0.15	Link
#7	Glm 4.5 Air Z Ai	$0.11	85.71%	15	03/21, 08:41	$0.15	Link
#8	Minimax M2.5 Minimax	$0.14	87.82%	15	03/21, 08:38	$0.18	Link
#9	Gemini 2.5 Flash Google	$0.17	70.73%	16	03/21, 09:15	$0.23	Link
#10	Llama 4 Maverick Meta Llama	$0.20	46.12%	9	03/19, 11:40	$0.37	Link

Gpt Oss 120b Openai

Lowest cost $0.03

Average cost $0.04 · Success rate 60.61%

Qwen 2.5 7b Instruct Qwen

Lowest cost $0.06

Average cost $0.08 · Success rate 40.29%

Qwen3.5 35b A3b Qwen

Lowest cost $0.07

Average cost $0.27 · Success rate 78.35%

Mercury 2 Inception

Lowest cost $0.07

Average cost $0.11 · Success rate 78.01%

Deepseek Chat Deepseek

Lowest cost $0.08

Average cost $0.19 · Success rate 71.69%

Minimax M2.1 Minimax

Lowest cost $0.11

Average cost $0.15 · Success rate 84.27%

Glm 4.5 Air Z Ai

Lowest cost $0.11

Average cost $0.15 · Success rate 85.71%

Minimax M2.5 Minimax

Lowest cost $0.14

Average cost $0.18 · Success rate 87.82%

Gemini 2.5 Flash Google

Lowest cost $0.17

Average cost $0.23 · Success rate 70.73%

#10

Llama 4 Maverick Meta Llama

Lowest cost $0.20

Average cost $0.37 · Success rate 46.12%

Link

Top Apps

Activity rankings for AI apps.

Week See the most active AI apps over the past week.

Mar 26, 2026, 3:00 PM

Rank	App	Usage	Link
#1	OpenClaw The AI that actually does things	799B	Link
#2	Kilo Code AI coding agent for VS Code	212B	Link
#3	Claude Code The AI for problem solvers	115B	Link
#4	Cline Autonomous coding agent right in your IDE	71.1B	Link
#5	Descript AI Video & Podcast Editor	48.2B	Link
#6	Janitor AI Character chat and creation	27.2B	Link
#7	ISEKAI ZERO AI adventures. Travel with your favorite characters	24.9B	Link
#8	Roo Code A whole dev team of AI agents in your editor	15.3B	Link
#9	Hermes Agent Control panel for AI apps	9.86B	Link

OpenClaw The AI that actually does things

Usage 799B

Kilo Code AI coding agent for VS Code

Usage 212B

Claude Code The AI for problem solvers

Usage 115B

Cline Autonomous coding agent right in your IDE

Usage 71.1B

Descript AI Video & Podcast Editor

Usage 48.2B

Janitor AI Character chat and creation

Usage 27.2B

ISEKAI ZERO AI adventures. Travel with your favorite characters

Usage 24.9B

Roo Code A whole dev team of AI agents in your editor

Usage 15.3B

Hermes Agent Control panel for AI apps

Usage 9.86B

Link

Day See the most active AI apps over the past day.

Mar 26, 2026, 3:00 PM

Rank	App	Usage	Link
#1	OpenClaw The AI that actually does things	799B	Link
#2	Kilo Code AI coding agent for VS Code	212B	Link
#3	Claude Code The AI for problem solvers	115B	Link
#4	Cline Autonomous coding agent right in your IDE	71.1B	Link
#5	Descript AI Video & Podcast Editor	48.2B	Link
#6	Janitor AI Character chat and creation	27.2B	Link
#7	ISEKAI ZERO AI adventures. Travel with your favorite characters	24.9B	Link
#8	Roo Code A whole dev team of AI agents in your editor	15.3B	Link
#9	Hermes Agent Control panel for AI apps	9.86B	Link

OpenClaw The AI that actually does things

Usage 799B

Kilo Code AI coding agent for VS Code

Usage 212B

Claude Code The AI for problem solvers

Usage 115B

Cline Autonomous coding agent right in your IDE

Usage 71.1B

Descript AI Video & Podcast Editor

Usage 48.2B

Janitor AI Character chat and creation

Usage 27.2B

ISEKAI ZERO AI adventures. Travel with your favorite characters

Usage 24.9B

Roo Code A whole dev team of AI agents in your editor

Usage 15.3B

Hermes Agent Control panel for AI apps

Usage 9.86B

Link

Month See the most active AI apps over the past month.

Mar 26, 2026, 3:00 PM

Rank	App	Usage	Link
#1	OpenClaw The AI that actually does things	799B	Link
#2	Kilo Code AI coding agent for VS Code	212B	Link
#3	Claude Code The AI for problem solvers	115B	Link
#4	Cline Autonomous coding agent right in your IDE	71.1B	Link
#5	Descript AI Video & Podcast Editor	48.2B	Link
#6	Janitor AI Character chat and creation	27.2B	Link
#7	ISEKAI ZERO AI adventures. Travel with your favorite characters	24.9B	Link
#8	Roo Code A whole dev team of AI agents in your editor	15.3B	Link
#9	Hermes Agent Control panel for AI apps	9.86B	Link

OpenClaw The AI that actually does things

Usage 799B

Kilo Code AI coding agent for VS Code

Usage 212B

Claude Code The AI for problem solvers

Usage 115B

Cline Autonomous coding agent right in your IDE

Usage 71.1B

Descript AI Video & Podcast Editor

Usage 48.2B

Janitor AI Character chat and creation

Usage 27.2B

ISEKAI ZERO AI adventures. Travel with your favorite characters

Usage 24.9B

Roo Code A whole dev team of AI agents in your editor

Usage 15.3B

Hermes Agent Control panel for AI apps

Usage 9.86B

Link

LLM

Usage and benchmark rankings for language models.

Week Track model usage and momentum over the past week.

Mar 26, 2026, 3:00 PM

Rank	Model	Usage	Context	Link
#1	Mimo V2 Pro Xiaomi	2.97T	1.0M	Link
#2	Step 3.5 Flash (free) StepFun	1.57T	256K	Link
#3	Deepseek V3.2 DeepSeek	1.18T	164K	Link
#4	Minimax M2.5 MiniMax	1.1T	197K	Link
#5	GLM 5 Turbo Z.ai	1.08T	203K	Link
#6	Claude Sonnet 4.6 Anthropic	1.04T	1.0M	Link
#7	Claude Opus 4.6 Anthropic	1.02T	1.0M	Link
#8	Gemini 3 Flash Preview Google	944B	1.0M	Link
#9	Minimax M2.7 MiniMax	926B	205K	Link
#10	Kimi K2.5 0127 MoonshotAI	558B	262K	Link

Mimo V2 Pro Xiaomi

Usage 2.97T

Context 1.0M

Step 3.5 Flash (free) StepFun

Usage 1.57T

Context 256K

Deepseek V3.2 DeepSeek

Usage 1.18T

Context 164K

Minimax M2.5 MiniMax

Usage 1.1T

Context 197K

GLM 5 Turbo Z.ai

Usage 1.08T

Context 203K

Claude Sonnet 4.6 Anthropic

Usage 1.04T

Context 1.0M

Claude Opus 4.6 Anthropic

Usage 1.02T

Context 1.0M

Gemini 3 Flash Preview Google

Usage 944B

Context 1.0M

Minimax M2.7 MiniMax

Usage 926B

Context 205K

#10

Kimi K2.5 0127 MoonshotAI

Usage 558B

Context 262K

Link

Day Track model usage and momentum over the past day.

Mar 26, 2026, 3:00 PM

Rank	Model	Usage	Context	Link
#1	Mimo V2 Pro Xiaomi	481B	1.0M	Link
#2	Step 3.5 Flash (free) StepFun	225B	256K	Link
#3	Minimax M2.7 MiniMax	211B	205K	Link
#4	Claude Sonnet 4.6 Anthropic	177B	1.0M	Link
#5	Deepseek V3.2 DeepSeek	177B	164K	Link
#6	Claude Opus 4.6 Anthropic	164B	1.0M	Link
#7	Minimax M2.5 MiniMax	161B	197K	Link
#8	Gemini 3 Flash Preview Google	159B	1.0M	Link
#9	GLM 5 Turbo Z.ai	142B	203K	Link
#10	Gemini 2.5 Flash Lite Google	90.9B	1.0M	Link

Mimo V2 Pro Xiaomi

Usage 481B

Context 1.0M

Step 3.5 Flash (free) StepFun

Usage 225B

Context 256K

Minimax M2.7 MiniMax

Usage 211B

Context 205K

Claude Sonnet 4.6 Anthropic

Usage 177B

Context 1.0M

Deepseek V3.2 DeepSeek

Usage 177B

Context 164K

Claude Opus 4.6 Anthropic

Usage 164B

Context 1.0M

Minimax M2.5 MiniMax

Usage 161B

Context 197K

Gemini 3 Flash Preview Google

Usage 159B

Context 1.0M

GLM 5 Turbo Z.ai

Usage 142B

Context 203K

#10

Gemini 2.5 Flash Lite Google

Usage 90.9B

Context 1.0M

Link

Month Track model usage and momentum over the past month.

Mar 26, 2026, 3:00 PM

Rank	Model	Usage	Context	Link
#1	Minimax M2.5 MiniMax	6.79T	197K	Link
#2	Step 3.5 Flash (free) StepFun	4.62T	256K	Link
#3	Gemini 3 Flash Preview Google	4.33T	1.0M	Link
#4	Deepseek V3.2 DeepSeek	4.22T	164K	Link
#5	Claude Sonnet 4.6 Anthropic	3.67T	1.0M	Link
#6	Claude Opus 4.6 Anthropic	3.6T	1.0M	Link
#7	Mimo V2 Pro Xiaomi	2.97T	1.0M	Link
#8	Kimi K2.5 0127 MoonshotAI	2.72T	262K	Link
#9	Gemini 2.5 Flash Google	2.35T	1.0M	Link
#10	Grok 4.1 Fast xAI	2.33T	2.0M	Link

Minimax M2.5 MiniMax

Usage 6.79T

Context 197K

Step 3.5 Flash (free) StepFun

Usage 4.62T

Context 256K

Gemini 3 Flash Preview Google

Usage 4.33T

Context 1.0M

Deepseek V3.2 DeepSeek

Usage 4.22T

Context 164K

Claude Sonnet 4.6 Anthropic

Usage 3.67T

Context 1.0M

Claude Opus 4.6 Anthropic

Usage 3.6T

Context 1.0M

Mimo V2 Pro Xiaomi

Usage 2.97T

Context 1.0M

Kimi K2.5 0127 MoonshotAI

Usage 2.72T

Context 262K

Gemini 2.5 Flash Google

Usage 2.35T

Context 1.0M

#10

Grok 4.1 Fast xAI

Usage 2.33T

Context 2.0M

Link

All rankings

Open any ranking page directly, including the agentic and coding benchmark views.

LLM / Weekly Track model usage and momentum over the past week. LLM / Daily Track model usage and momentum over the past day. LLM / Monthly Track model usage and momentum over the past month. Top Apps / Weekly See the most active AI apps over the past week. Top Apps / Daily See the most active AI apps over the past day. Top Apps / Monthly See the most active AI apps over the past month. LLM / Agentic Compare model performance on agentic benchmark tasks. LLM / Coding Compare model performance on coding benchmark tasks. OpenClaw / Score See which models score best on the OpenClaw task set. OpenClaw / Speed See which models finish OpenClaw tasks the fastest. OpenClaw / Cost See which models complete OpenClaw tasks at the lowest cost.