Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific QA on SPIQA
Loading...
79.9
SPIQA-A
GPT-5.2
58.788
64.269
69.75
75.231
Mar 12, 2026
SPIQA-A
SPIQA-B
SPIQA-C
Updated 4mo ago
Evaluation Results
Method
Method
Links
SPIQA-A
SPIQA-B
SPIQA-C
GPT-5.2
Model=GPT-5.2
2026.03
79.9
75.4
74
GPT-5.1
Model=GPT-5.1
2026.03
79.4
79.8
71.6
Qwen-3-VL-8B
Model=Qwen-3-VL-8B
2026.03
73.2
64
62.3
Qwen2.5-VL-7B + SCIMDR
Model=Qwen2.5-VL-7B, T...
2026.03
68.6
58.8
47.3
Qwen2.5-VL-7B
Model=Qwen2.5-VL-7B, T...
2026.03
66.4
56.6
48.9
LLaVA-OV-1.5-8B
Model=LLaVA-OV-1.5-8B
2026.03
66
62.7
51.1
Qwen2.5-VL-7B + SPIQA
Model=Qwen2.5-VL-7B, T...
2026.03
62.7
44.7
40
InternVL-3-8B
Model=InternVL-3-8B
2026.03
59.6
46.9
40.8
Feedback
Search any
task
Search any
task