OpenClaw Model Rankings
Top 10 of 44 qualifying models
OpenAI
63.4
OpenClaw
Intelligence · Coding
Int 42.1·Code 76.7
Terminal-Bench Hard
57.6%
Latency (TTFT)
199.30 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
OpenAI
61.7
OpenClaw
Intelligence · Coding
Int 38.0·Code 70.6
Terminal-Bench Hard
62.9%
Latency (TTFT)
10.56 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
Alibaba
61.0
OpenClaw
Intelligence · Coding
Int 25.2·Code 55.9
Terminal-Bench Hard
47.0%
Latency (TTFT)
1.62 s
Run Cost
$0.011
in $0.400 / out $1.600 per 1M
OpenAI
60.1
OpenClaw
Intelligence · Coding
Int 34.2·Code 67.1
Terminal-Bench Hard
57.6%
Latency (TTFT)
6.57 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
MiniMax
59.5
OpenClaw
Intelligence · Coding
Int 29.2·Code 58.6
Terminal-Bench Hard
42.4%
Latency (TTFT)
863 ms
Run Cost
$0.0084
in $0.300 / out $1.200 per 1M
Kimi
56.1
OpenClaw
Intelligence · Coding
Int 25.8·Code 60.8
Terminal-Bench Hard
44.7%
Latency (TTFT)
1.33 s
Run Cost
$0.027
in $0.950 / out $4.000 per 1M
56.0
OpenClaw
Intelligence · Coding
Int 29.7·Code 68.8
Terminal-Bench Hard
53.8%
Latency (TTFT)
16.09 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
Alibaba
51.1
OpenClaw
Intelligence · Coding
Int 18.4·Code 48.2
Terminal-Bench Hard
40.9%
Latency (TTFT)
1.64 s
Run Cost
$0.022
in $0.600 / out $3.600 per 1M
49.8
OpenClaw
Intelligence · Coding
Int 22.9·Code 49.3
Terminal-Bench Hard
36.4%
Latency (TTFT)
801 ms
Run Cost
$0.018
in $0.600 / out $2.700 per 1M
Alibaba
47.5
OpenClaw
Intelligence · Coding
Int 18.2·Code 41.9
Terminal-Bench Hard
34.8%
Latency (TTFT)
1.16 s
Run Cost
$0.014
in $0.375 / out $2.250 per 1M
| # | Model | OpenClaw Score | Intelligence · Coding | Terminal-Bench Hard | Latency (TTFT) | Run Cost | Value |
|---|---|---|---|---|---|---|---|
| #1 | GPT-5.6 Terra (Max) OpenAI | 63.4 | Int 42.1·Code 76.7 Capability 45.6 | 57.6% Score 100.0 | 199.30 s Speed score 1.0 | $0.072 in $2.000 / out $12.000 per 1M | 21.7 |
| #2 | GPT-5.6 Terra (Xhigh) OpenAI | 61.7 | Int 38.0·Code 70.6 Capability 41.3 | 62.9% Score 100.0 | 10.56 s Speed score 15.1 | $0.072 in $2.000 / out $12.000 per 1M | 18.4 |
| #3 | Qwen3.7 Plus Alibaba | 61.0 | Int 25.2·Code 55.9 Capability 28.3 | 47.0% Score 81.8 | 1.62 s Speed score 75.0 | $0.011 in $0.400 / out $1.600 per 1M | 45.8 |
| #4 | GPT-5.6 Terra (High) OpenAI | 60.1 | Int 34.2·Code 67.1 Capability 37.5 | 57.6% Score 100.0 | 6.57 s Speed score 32.2 | $0.072 in $2.000 / out $12.000 per 1M | 15.5 |
| #5 | MiniMax-M3 MiniMax | 59.5 | Int 29.2·Code 58.6 Capability 32.1 | 42.4% Score 73.6 | 863 ms Speed score 88.8 | $0.0084 in $0.300 / out $1.200 per 1M | 66.0 |
| #6 | Kimi K2.7 Code Kimi | 56.1 | Int 25.8·Code 60.8 Capability 29.3 | 44.7% Score 77.7 | 1.33 s Speed score 79.7 | $0.027 in $0.950 / out $4.000 per 1M | 22.6 |
| #7 | Gemini 3.1 Pro Preview | 56.0 | Int 29.7·Code 68.8 Capability 33.6 | 53.8% Score 94.2 | 16.09 s Speed score 1.0 | $0.072 in $2.000 / out $12.000 per 1M | 12.4 |
| #8 | Qwen3.5 397B A17B (Reasoning) Alibaba | 51.1 | Int 18.4·Code 48.2 Capability 21.4 | 40.9% Score 70.9 | 1.64 s Speed score 74.7 | $0.022 in $0.600 / out $3.600 per 1M | 16.7 |
| #9 | Nemotron 3 Ultra 550B A55B (Reasoning) NVIDIA | 49.8 | Int 22.9·Code 49.3 Capability 25.5 | 36.4% Score 62.6 | 801 ms Speed score 90.1 | $0.018 in $0.600 / out $2.700 per 1M | 26.7 |
| #10 | Qwen3.6 35B A3B (Reasoning) Alibaba | 47.5 | Int 18.2·Code 41.9 Capability 20.6 | 34.8% Score 59.9 | 1.16 s Speed score 82.9 | $0.014 in $0.375 / out $2.250 per 1M | 25.6 |
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.