Geolocalization on MAPBench 1.0 (test-hard) benchmark leaderboard · SOTA2 Research

Geolocalization on MAPBench 1.0 (test-hard)

14.86Acc@500mThinking with Map + Reinforcement Learning + Parallelx4 & Verifier

Evaluation Results

Method
Thinking with Map + Reinforcement Learning + Parallelx4 & Verifier2026.01	14.86	17.4	29.88	34.37	45.21	68.85
Thinking with Map + Reinforcement Learning + Parallelx2 & Verifier2026.01	13.7	16.45	28.98	33.79	44.32	68.85
Thinking with Map + Reinforcement Learning2026.01	12.33	14.67	26.89	31.62	42.58	67.17
Thinking with Map2026.01	10.83	12.05	16.08	19.06	25.58	38.28
Gemini-3-Pro2026.01	4.02	11.73	23.45	29.64	41.86	67.48
Qwen3-VL-235B-A22B2026.01	0.63	3.42	13.41	19.31	32.88	57.18
Qwen3-VL-30B-A3B2026.01	0.21	1.89	10.36	14.2	28.56	52.76
GPT-o32026.01	0.05	0.74	4.53	9.1	20.73	44.13
GPT-52026.01	0.05	0.79	4.1	8.94	22.3	47.45
GLOBE-7B2026.01	0.05	0.85	6.34	11.35	27.68	52.29
GeoVista-7B2026.01	0	0.53	4.16	6.52	10.94	18.99