OpenClaw Model Rankings
Top 10 of 64 qualifying models
OpenAI
75.6
OpenClaw
Intelligence · Coding
Int 52.8·Code 70.6
Terminal-Bench Hard
62.9%
Latency (TTFT)
12.75 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
OpenAI
73.3
OpenClaw
Intelligence · Coding
Int 56.6·Code 76.7
Terminal-Bench Hard
57.6%
Latency (TTFT)
88.13 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
70.6
OpenClaw
Intelligence · Coding
Int 62.1·Code 76.5
Terminal-Bench Hard
62.9%
Latency (TTFT)
48.43 s
Run Cost
$0.320
in $10.000 / out $50.000 per 1M
OpenAI
70.6
OpenClaw
Intelligence · Coding
Int 50.1·Code 67.1
Terminal-Bench Hard
57.6%
Latency (TTFT)
4.46 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
OpenAI
70.2
OpenClaw
Intelligence · Coding
Int 60.9·Code 77.4
Terminal-Bench Hard
65.9%
Latency (TTFT)
76.98 s
Run Cost
$0.180
in $5.000 / out $30.000 per 1M
OpenAI
68.5
OpenClaw
Intelligence · Coding
Int 59.0·Code 78.3
Terminal-Bench Hard
61.4%
Latency (TTFT)
25.46 s
Run Cost
$0.180
in $5.000 / out $30.000 per 1M
OpenAI
68.4
OpenClaw
Intelligence · Coding
Int 57.3·Code 77.2
Terminal-Bench Hard
62.1%
Latency (TTFT)
12.08 s
Run Cost
$0.180
in $5.000 / out $30.000 per 1M
OpenAI
68.2
OpenClaw
Intelligence · Coding
Int 55.6·Code 76.3
Terminal-Bench Hard
62.9%
Latency (TTFT)
5.54 s
Run Cost
$0.180
in $5.000 / out $30.000 per 1M
66.9
OpenClaw
Intelligence · Coding
Int 47.7·Code 68.8
Terminal-Bench Hard
53.8%
Latency (TTFT)
22.02 s
Run Cost
$0.072
in $2.000 / out $12.000 per 1M
DeepSeek
65.5
OpenClaw
Intelligence · Coding
Int 45.3·Code 59.4
Terminal-Bench Hard
46.2%
Latency (TTFT)
1.26 s
Run Cost
$0.0087
in $0.435 / out $0.870 per 1M
| # | Model | OpenClaw Score | Intelligence · Coding | Terminal-Bench Hard | Latency (TTFT) | Run Cost | Value |
|---|---|---|---|---|---|---|---|
| #1 | GPT-5.6 Terra (xhigh) OpenAI | 75.6 | Int 52.8·Code 70.6 Capability 54.6 | 62.9% Score 100.0 | 12.75 s Speed score 22.2 | $0.072 in $2.000 / out $12.000 per 1M | 12.6 |
| #2 | GPT-5.6 Terra (max) OpenAI | 73.3 | Int 56.6·Code 76.7 Capability 58.6 | 57.6% Score 91.3 | 88.13 s Speed score 1.0 | $0.072 in $2.000 / out $12.000 per 1M | 14.5 |
| #3 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic | 70.6 | Int 62.1·Code 76.5 Capability 63.5 | 62.9% Score 100.0 | 48.43 s Speed score 1.0 | $0.320 in $10.000 / out $50.000 per 1M | 4.7 |
| #4 | GPT-5.6 Terra (high) OpenAI | 70.6 | Int 50.1·Code 67.1 Capability 51.8 | 57.6% Score 91.3 | 4.46 s Speed score 54.5 | $0.072 in $2.000 / out $12.000 per 1M | 11.3 |
| #5 | GPT-5.6 Sol (max) OpenAI | 70.2 | Int 60.9·Code 77.4 Capability 62.6 | 65.9% Score 100.0 | 76.98 s Speed score 1.0 | $0.180 in $5.000 / out $30.000 per 1M | 7.9 |
| #6 | GPT-5.6 Sol (xhigh) OpenAI | 68.5 | Int 59.0·Code 78.3 Capability 60.9 | 61.4% Score 97.6 | 25.46 s Speed score 1.0 | $0.180 in $5.000 / out $30.000 per 1M | 7.3 |
| #7 | GPT-5.6 Sol (high) OpenAI | 68.4 | Int 57.3·Code 77.2 Capability 59.3 | 62.1% Score 98.9 | 12.08 s Speed score 23.9 | $0.180 in $5.000 / out $30.000 per 1M | 6.7 |
| #8 | GPT-5.6 Sol (medium) OpenAI | 68.2 | Int 55.6·Code 76.3 Capability 57.7 | 62.9% Score 100.0 | 5.54 s Speed score 48.2 | $0.180 in $5.000 / out $30.000 per 1M | 6.2 |
| #9 | Gemini 3.1 Pro Preview | 66.9 | Int 47.7·Code 68.8 Capability 49.8 | 53.8% Score 84.9 | 22.02 s Speed score 4.1 | $0.072 in $2.000 / out $12.000 per 1M | 10.4 |
| #10 | DeepSeek V4 Pro (Reasoning, Max Effort) DeepSeek | 65.5 | Int 45.3·Code 59.4 Capability 46.7 | 46.2% Score 72.2 | 1.26 s Speed score 85.3 | $0.0087 in $0.435 / out $0.870 per 1M | 53.4 |
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.