DeepSeek1 Dec 2025Model

DeepSeek-V3.2

Benchmark results

Benchmark	Score	Source check
Humanity's Last ExamNo tools · thinking mode; 21K output tokens; full or text-only set not stated	25.1%	Checked A person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 2 other lab documents: 1 2
SWE-bench Verifiedthinking mode	73.1%	Checked A person checked this number against its source on 17 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 6 other lab documents, the first 3 linked: 1 2 3
GPQA Diamondthinking mode; 7K output tokens	82.4%	Corroborated The same number is printed in 1 other lab document: 1
Terminal-Bench 2.0	46.4%	Checked A person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. Corroborated The same number is printed in 5 other lab documents, the first 3 linked: 1 2 3
AIME 2025No tools · 16K output tokens	93.1%	Checked A person checked this number against its source on 18 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced.

Sources

Reported by DeepSeek