cyberclaw.directory
Sign in

OpenClaw Rankings

Best models for OpenClaw usage

OpenClaw Model Rankings

Top 10 of 229 qualifying models

Score weights:45% Terminal-Bench40% Capability15% Cost
#1KAT Coder Pro V2

KwaiKAT

76.4

OpenClaw

Intelligence · Coding

Int 43.8·Code 45.6

Terminal-Bench Hard

49.2%

Latency (TTFT)

2.05 s

Run Cost

$0.0084

in $0.300 / out $1.200 per 1M

#2GPT-5.4 mini (xhigh)

OpenAI

75.2

OpenClaw

Intelligence · Coding

Int 48.1·Code 51.5

Terminal-Bench Hard

52.3%

Latency (TTFT)

5.07 s

Run Cost

$0.027

in $0.750 / out $4.500 per 1M

#3GPT-5.4 nano (xhigh)

OpenAI

74.5

OpenClaw

Intelligence · Coding

Int 44.4·Code 43.9

Terminal-Bench Hard

42.4%

Latency (TTFT)

2.52 s

Run Cost

$0.0074

in $0.200 / out $1.250 per 1M

#4GLM-5 (Reasoning)

Z AI

74.5

OpenClaw

Intelligence · Coding

Int 49.8·Code 44.2

Terminal-Bench Hard

43.2%

Latency (TTFT)

938 ms

Run Cost

$0.025

in $1.000 / out $3.200 per 1M

#5MiniMax-M2.7

MiniMax

73.1

OpenClaw

Intelligence · Coding

Int 49.6·Code 41.9

Terminal-Bench Hard

39.4%

Latency (TTFT)

2.18 s

Run Cost

$0.0084

in $0.300 / out $1.200 per 1M

#6Gemini 3.1 Pro Preview

Google

71.5

OpenClaw

Intelligence · Coding

Int 57.2·Code 55.5

Terminal-Bench Hard

53.8%

Latency (TTFT)

25.12 s

Run Cost

$0.072

in $2.000 / out $12.000 per 1M

#7Qwen3.5 397B A17B (Reasoning)

Alibaba

70.8

OpenClaw

Intelligence · Coding

Int 45.0·Code 41.3

Terminal-Bench Hard

40.9%

Latency (TTFT)

1.37 s

Run Cost

$0.022

in $0.600 / out $3.600 per 1M

#8GPT-5.1 (high)

OpenAI

70.3

OpenClaw

Intelligence · Coding

Int 47.7·Code 44.7

Terminal-Bench Hard

45.5%

Latency (TTFT)

21.79 s

Run Cost

$0.055

in $1.250 / out $10.000 per 1M

#9Gemini 3 Flash Preview (Reasoning)

Google

69.6

OpenClaw

Intelligence · Coding

Int 46.4·Code 42.6

Terminal-Bench Hard

38.6%

Latency (TTFT)

5.79 s

Run Cost

$0.018

in $0.500 / out $3.000 per 1M

#10GPT-5.3 Codex (xhigh)

OpenAI

69.5

OpenClaw

Intelligence · Coding

Int 54.0·Code 53.1

Terminal-Bench Hard

53.0%

Latency (TTFT)

62.96 s

Run Cost

$0.077

in $1.750 / out $14.000 per 1M

Scores (0–100) are percentile-normalized across all qualifying models — not raw benchmark percentages. Standard run = 12,000 input + 4,000 output tokens. Hover column headers for metric definitions. Data via Artificial Analysis.

Value Map

Best models cluster top-left: high Intelligence Index, low run cost. Bubble size scales with Terminal-Bench Hard score. Hover a bubble or legend entry to inspect.

Scroll horizontally to explore →

← cheaper · smarter ↑ (ideal zone)$0.0024$0.0069$0.020$0.056$0.1602534445363Run Cost per call, log scale →Intelligence Index →KAT Coder Pro V2 Provider: KwaiKAT OpenClaw Score: 76.4 Intelligence Index: 43.8 Agent Fitness: 44.0 Terminal-Bench Hard: 49.2% Latency (TTFT): 2.05 s Run cost: $0.0084GPT-5.4 mini (xhigh) Provider: OpenAI OpenClaw Score: 75.2 Intelligence Index: 48.1 Agent Fitness: 48.4 Terminal-Bench Hard: 52.3% Latency (TTFT): 5.07 s Run cost: $0.027GPT-5.4 nano (xhigh) Provider: OpenAI OpenClaw Score: 74.5 Intelligence Index: 44.4 Agent Fitness: 44.4 Terminal-Bench Hard: 42.4% Latency (TTFT): 2.52 s Run cost: $0.0074GLM-5 (Reasoning) Provider: Z AI OpenClaw Score: 74.5 Intelligence Index: 49.8 Agent Fitness: 49.2 Terminal-Bench Hard: 43.2% Latency (TTFT): 938 ms Run cost: $0.025MiniMax-M2.7 Provider: MiniMax OpenClaw Score: 73.1 Intelligence Index: 49.6 Agent Fitness: 48.8 Terminal-Bench Hard: 39.4% Latency (TTFT): 2.18 s Run cost: $0.0084Gemini 3.1 Pro Preview Provider: Google OpenClaw Score: 71.5 Intelligence Index: 57.2 Agent Fitness: 57.0 Terminal-Bench Hard: 53.8% Latency (TTFT): 25.12 s Run cost: $0.072Qwen3.5 397B A17B (Reasoning) Provider: Alibaba OpenClaw Score: 70.8 Intelligence Index: 45.0 Agent Fitness: 44.6 Terminal-Bench Hard: 40.9% Latency (TTFT): 1.37 s Run cost: $0.022GPT-5.1 (high) Provider: OpenAI OpenClaw Score: 70.3 Intelligence Index: 47.7 Agent Fitness: 47.4 Terminal-Bench Hard: 45.5% Latency (TTFT): 21.79 s Run cost: $0.055Gemini 3 Flash Preview (Reasoning) Provider: Google OpenClaw Score: 69.6 Intelligence Index: 46.4 Agent Fitness: 46.0 Terminal-Bench Hard: 38.6% Latency (TTFT): 5.79 s Run cost: $0.018GPT-5.3 Codex (xhigh) Provider: OpenAI OpenClaw Score: 69.5 Intelligence Index: 54.0 Agent Fitness: 53.9 Terminal-Bench Hard: 53.0% Latency (TTFT): 62.96 s Run cost: $0.077GPT-5.4 (xhigh) Provider: OpenAI OpenClaw Score: 68.8 Intelligence Index: 57.2 Agent Fitness: 57.2 Terminal-Bench Hard: 57.6% Latency (TTFT): 169.08 s Run cost: $0.090GPT-5.2 (xhigh) Provider: OpenAI OpenClaw Score: 68.3 Intelligence Index: 51.3 Agent Fitness: 51.0 Terminal-Bench Hard: 47.0% Latency (TTFT): 83.45 s Run cost: $0.077Grok 4.20 Beta 0309 (Reasoning) Provider: xAI OpenClaw Score: 67.9 Intelligence Index: 48.5 Agent Fitness: 47.9 Terminal-Bench Hard: 40.9% Latency (TTFT): 10.80 s Run cost: $0.048GLM-5 (Non-reasoning) Provider: Z AI OpenClaw Score: 67.1 Intelligence Index: 40.6 Agent Fitness: 40.4 Terminal-Bench Hard: 39.4% Latency (TTFT): 1.16 s Run cost: $0.025DeepSeek V3.2 (Reasoning) Provider: DeepSeek OpenClaw Score: 66.8 Intelligence Index: 41.7 Agent Fitness: 41.2 Terminal-Bench Hard: 35.6% Latency (TTFT): 1.43 s Run cost: $0.0050Claude Opus 4.6 (Adaptive Reasoning, Max Effort) Provider: Anthropic OpenClaw Score: 66.2 Intelligence Index: 53.0 Agent Fitness: 52.5 Terminal-Bench Hard: 46.2% Latency (TTFT): 9.07 s Run cost: $0.160Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) Provider: Anthropic OpenClaw Score: 65.8 Intelligence Index: 51.7 Agent Fitness: 51.6 Terminal-Bench Hard: 53.0% Latency (TTFT): 35.81 s Run cost: $0.096Kimi K2.5 (Reasoning) Provider: Kimi OpenClaw Score: 65.6 Intelligence Index: 46.8 Agent Fitness: 46.1 Terminal-Bench Hard: 34.8% Latency (TTFT): 3.88 s Run cost: $0.019MiniMax-M2.5 Provider: MiniMax OpenClaw Score: 65.5 Intelligence Index: 41.9 Agent Fitness: 41.4 Terminal-Bench Hard: 34.8% Latency (TTFT): 1.11 s Run cost: $0.0084Gemini 3 Pro Preview (high) Provider: Google OpenClaw Score: 65.1 Intelligence Index: 48.4 Agent Fitness: 48.2 Terminal-Bench Hard: 41.7% Latency (TTFT): 25.28 s Run cost: $0.072Claude Opus 4.5 (Reasoning) Provider: Anthropic OpenClaw Score: 65.0 Intelligence Index: 49.7 Agent Fitness: 49.5 Terminal-Bench Hard: 47.0% Latency (TTFT): 10.39 s Run cost: $0.160Claude Opus 4.6 (Non-reasoning, High Effort) Provider: Anthropic OpenClaw Score: 63.8 Intelligence Index: 46.5 Agent Fitness: 46.6 Terminal-Bench Hard: 48.5% Latency (TTFT): 1.75 s Run cost: $0.160Qwen3.5 397B A17B (Non-reasoning) Provider: Alibaba OpenClaw Score: 63.5 Intelligence Index: 40.1 Agent Fitness: 39.8 Terminal-Bench Hard: 35.6% Latency (TTFT): 1.39 s Run cost: $0.022GPT-5 mini (high) Provider: OpenAI OpenClaw Score: 63.3 Intelligence Index: 41.2 Agent Fitness: 40.6 Terminal-Bench Hard: 33.3% Latency (TTFT): 88.20 s Run cost: $0.011Claude Sonnet 4.6 (Non-reasoning, High Effort) Provider: Anthropic OpenClaw Score: 63.0 Intelligence Index: 44.4 Agent Fitness: 44.6 Terminal-Bench Hard: 46.2% Latency (TTFT): 1.46 s Run cost: $0.096GPT-5.4 nano (medium) Provider: OpenAI OpenClaw Score: 62.7 Intelligence Index: 38.1 Agent Fitness: 37.8 Terminal-Bench Hard: 33.3% Latency (TTFT): 1.51 s Run cost: $0.0074Qwen3.5 27B (Reasoning) Provider: Alibaba OpenClaw Score: 62.5 Intelligence Index: 42.1 Agent Fitness: 41.4 Terminal-Bench Hard: 32.6% Latency (TTFT): 1.30 s Run cost: $0.013MiMo-V2-Flash (Feb 2026) Provider: Xiaomi OpenClaw Score: 62.5 Intelligence Index: 41.5 Agent Fitness: 40.7 Terminal-Bench Hard: 31.1% Latency (TTFT): 1.36 s Run cost: $0.0024GPT-5.1 Codex mini (high) Provider: OpenAI OpenClaw Score: 62.4 Intelligence Index: 38.6 Agent Fitness: 38.4 Terminal-Bench Hard: 33.3% Latency (TTFT): 4.03 s Run cost: $0.011GPT-5 Codex (high) Provider: OpenAI OpenClaw Score: 62.2 Intelligence Index: 44.6 Agent Fitness: 44.0 Terminal-Bench Hard: 37.9% Latency (TTFT): 7.27 s Run cost: $0.055GLM-4.7 (Reasoning) Provider: Z AI OpenClaw Score: 61.3 Intelligence Index: 42.1 Agent Fitness: 41.5 Terminal-Bench Hard: 31.8% Latency (TTFT): 702 ms Run cost: $0.016GPT-5 (medium) Provider: OpenAI OpenClaw Score: 61.3 Intelligence Index: 42.0 Agent Fitness: 41.7 Terminal-Bench Hard: 37.9% Latency (TTFT): 41.72 s Run cost: $0.055GPT-5.4 mini (medium) Provider: OpenAI OpenClaw Score: 60.3 Intelligence Index: 37.7 Agent Fitness: 37.7 Terminal-Bench Hard: 34.1% Latency (TTFT): 6.68 s Run cost: $0.027DeepSeek V3.2 (Non-reasoning) Provider: DeepSeek OpenClaw Score: 60.2 Intelligence Index: 32.1 Agent Fitness: 32.4 Terminal-Bench Hard: 32.6% Latency (TTFT): 1.42 s Run cost: $0.0050Qwen3.5 122B A10B (Reasoning) Provider: Alibaba OpenClaw Score: 60.1 Intelligence Index: 41.6 Agent Fitness: 40.9 Terminal-Bench Hard: 31.1% Latency (TTFT): 1.06 s Run cost: $0.018Claude Sonnet 4.6 (Non-reasoning, Low Effort) Provider: Anthropic OpenClaw Score: 60.0 Intelligence Index: 42.6 Agent Fitness: 42.6 Terminal-Bench Hard: 42.4% Latency (TTFT): 1.49 s Run cost: $0.096Kimi K2 Thinking Provider: Kimi OpenClaw Score: 59.9 Intelligence Index: 40.9 Agent Fitness: 40.3 Terminal-Bench Hard: 31.1% Latency (TTFT): 849 ms Run cost: $0.017Qwen3.5 27B (Non-reasoning) Provider: Alibaba OpenClaw Score: 59.9 Intelligence Index: 37.2 Agent Fitness: 36.8 Terminal-Bench Hard: 31.8% Latency (TTFT): 1.34 s Run cost: $0.013GPT-5.2 Codex (xhigh) Provider: OpenAI OpenClaw Score: 59.7 Intelligence Index: 49.0 Agent Fitness: 48.4 Terminal-Bench Hard: 37.1% Latency (TTFT): 3.77 s Run cost: $0.077o3 Provider: OpenAI OpenClaw Score: 59.0 Intelligence Index: 38.4 Agent Fitness: 38.4 Terminal-Bench Hard: 37.1% Latency (TTFT): 7.08 s Run cost: $0.056DeepSeek V3.2 Exp (Reasoning) Provider: DeepSeek OpenClaw Score: 59.0 Intelligence Index: 32.9 Agent Fitness: 32.9 Terminal-Bench Hard: 31.1% Latency (TTFT): 1.32 s Run cost: $0.0050Claude Opus 4.5 (Non-reasoning) Provider: Anthropic OpenClaw Score: 58.7 Intelligence Index: 43.1 Agent Fitness: 43.1 Terminal-Bench Hard: 40.9% Latency (TTFT): 1.26 s Run cost: $0.160Gemini 3 Flash Preview (Non-reasoning) Provider: Google OpenClaw Score: 58.5 Intelligence Index: 35.0 Agent Fitness: 35.3 Terminal-Bench Hard: 31.8% Latency (TTFT): 8.00 s Run cost: $0.018MiMo-V2-Flash (Reasoning) Provider: Xiaomi OpenClaw Score: 58.5 Intelligence Index: 39.2 Agent Fitness: 38.5 Terminal-Bench Hard: 28.0% Latency (TTFT): 1.53 s Run cost: $0.0024GPT-5.1 Codex (high) Provider: OpenAI OpenClaw Score: 58.4 Intelligence Index: 43.1 Agent Fitness: 42.5 Terminal-Bench Hard: 34.8% Latency (TTFT): 5.27 s Run cost: $0.055MiniMax-M2.1 Provider: MiniMax OpenClaw Score: 58.4 Intelligence Index: 39.4 Agent Fitness: 38.7 Terminal-Bench Hard: 28.8% Latency (TTFT): 1.56 s Run cost: $0.0084GPT-5 mini (medium) Provider: OpenAI OpenClaw Score: 57.8 Intelligence Index: 38.9 Agent Fitness: 38.3 Terminal-Bench Hard: 28.8% Latency (TTFT): 15.98 s Run cost: $0.011NVIDIA Nemotron 3 Super 120B A12B (Reasoning) Provider: NVIDIA OpenClaw Score: 57.4 Intelligence Index: 36.0 Agent Fitness: 35.5 Terminal-Bench Hard: 28.8% Latency (TTFT): 675 ms Run cost: $0.0066Step 3.5 Flash Provider: StepFun OpenClaw Score: 57.2 Intelligence Index: 37.8 Agent Fitness: 37.2 Terminal-Bench Hard: 27.3% Latency (TTFT): 2.65 s Run cost: $0.0024GLM-4.7 (Non-reasoning) Provider: Z AI OpenClaw Score: 56.9 Intelligence Index: 34.2 Agent Fitness: 34.0 Terminal-Bench Hard: 30.3% Latency (TTFT): 684 ms Run cost: $0.015GPT-5 (high) Provider: OpenAI OpenClaw Score: 56.7 Intelligence Index: 44.6 Agent Fitness: 43.7 Terminal-Bench Hard: 32.6% Latency (TTFT): 73.19 s Run cost: $0.055Qwen3.5 122B A10B (Non-reasoning) Provider: Alibaba OpenClaw Score: 56.3 Intelligence Index: 35.9 Agent Fitness: 35.5 Terminal-Bench Hard: 29.5% Latency (TTFT): 999 ms Run cost: $0.018Grok 4 Provider: xAI OpenClaw Score: 55.0 Intelligence Index: 41.5 Agent Fitness: 41.4 Terminal-Bench Hard: 37.9% Latency (TTFT): 8.11 s Run cost: $0.096Qwen3.5 35B A3B (Reasoning) Provider: Alibaba OpenClaw Score: 54.7 Intelligence Index: 37.1 Agent Fitness: 36.4 Terminal-Bench Hard: 26.5% Latency (TTFT): 1.06 s Run cost: $0.011Grok 4.1 Fast (Reasoning) Provider: xAI OpenClaw Score: 54.0 Intelligence Index: 38.6 Agent Fitness: 37.8 Terminal-Bench Hard: 24.2% Latency (TTFT): 7.62 s Run cost: $0.0044MiniMax-M2 Provider: MiniMax OpenClaw Score: 54.0 Intelligence Index: 36.1 Agent Fitness: 35.4 Terminal-Bench Hard: 25.8% Latency (TTFT): 1.44 s Run cost: $0.0084Mercury 2 Provider: Inception OpenClaw Score: 54.0 Intelligence Index: 32.8 Agent Fitness: 32.6 Terminal-Bench Hard: 26.5% Latency (TTFT): 3.52 s Run cost: $0.0060GLM-4.6 (Non-reasoning) Provider: Z AI OpenClaw Score: 53.7 Intelligence Index: 30.2 Agent Fitness: 30.2 Terminal-Bench Hard: 28.8% Latency (TTFT): 973 ms Run cost: $0.016GPT-5.4 (Non-reasoning) Provider: OpenAI OpenClaw Score: 53.6 Intelligence Index: 35.4 Agent Fitness: 36.0 Terminal-Bench Hard: 37.9% Latency (TTFT): 531 ms Run cost: $0.090Claude 4.5 Sonnet (Reasoning) Provider: Anthropic OpenClaw Score: 53.1 Intelligence Index: 43.0 Agent Fitness: 42.6 Terminal-Bench Hard: 35.6% Latency (TTFT): 8.01 s Run cost: $0.096

Data provided by Artificial Analysis