Our new X account is live! Follow @wizwand_team for updates

Robotic Manipulation Planning on ALRM Benchmark

54Score 0

Granite-3.3-8B

Updated 4d ago

Evaluation Results

Method	Links
Granite-3.3-8B 2026.01		54	0	0	0	0	0	0	0	0	19.07
Mistral-7B 2026.01		54	0	0	0	0	0	0	0	0	10.81
Llama-3.1-8B 2026.01		50	4	0	5.6	0	0	5.6	5.6	3.7	36.07
Mistral-7B 2026.01		45	9	0	11.1	11.1	5.6	5.6	8.3	8.3	18.96
Falcon-H1-7B 2026.01		38	16	0	27.8	16.7	16.7	0	13.9	14.8	161.34
DeepSeek-R1-7B 2026.01		31	23	0	33.3	5.6	5.6	27.8	27.8	21.3	53.55
Qwen3-8B 2026.01		7	24	23	66.7	72.2	88.9	61.1	50	64.8	343.33
Granite-3.3-8B 2026.01		6	38	10	61.1	56.6	56.6	44.4	52.8	53.7	24.48
Qwen3-8B 2026.01		5	40	9	55.6	61.1	55.6	55.6	47.2	53.7	392.08
Llama-3.1-8B 2026.01		2	28	24	72.2	77.8	77.8	77.8	58.3	68.5	20.13
Claude-4.1-Opus 2026.01		0	8	46	94.4	94.4	94.4	88.9	91.7	92.6	33.44
GPT-5 2026.01		0	10	44	88.9	94.4	100	88.9	86.1	90.7	145.59
DeepSeek-V3.1 2026.01		0	17	37	88.9	88.9	83.3	83.3	80.6	84.3	69.83
Gemini-2.5-Pro 2026.01		0	29	25	72.2	77.8	66.7	77.8	72.2	73.1	52.62
Falcon-H1-7B 2026.01		0	17	37	83.3	88.9	88.9	88.9	77.8	84.3	24.89
Claude-4.1-Opus 2026.01		0	7	47	94.4	94.4	94.4	94.4	91.7	93.5	82.6
GPT-5 2026.01		0	16	38	94.4	100	72.2	72.2	86.1	85.2	113.88
DeepSeek-V3.1 2026.01		0	16	38	88.9	94.4	83.3	83.3	80.6	85.2	161.73
Gemini-2.5-Pro 2026.01		0	14	40	88.9	94.4	77.8	88.9	86.1	87	117.43