Model record

DeepSeek V3.2

Open weights

DeepSeek · released Dec 1, 2025

Overall standing

Overall
42.4rank 47 of 62
42.4 is at approximately the 25th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
8 of 8 measured
Category standingsReasoning 58.0Coding 42.9Math 2.9Agentic 18.8
Reasoning
58.0rank 45 of 62
58.0 is at approximately the 28th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
42.9rank 39 of 46
42.9 is at approximately the 16th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 56.1.
2 of 2 measured
Math
2.9rank 39 of 62
2.9 is at approximately the 36th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
18.8rank 26 of 46
18.8 is at approximately the 45th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.6.
1 of 1 measured
Model factsOpen weights · $0.28 / $0.42 per 1M

Copied from the linked provider page; no separate retrieval date is stored.

Provider
DeepSeek
Released
Weights
Open weights
Context window
128,000 tokens
Input price / Mtok
$0.28
Output price / Mtok
$0.42
Reasoning effort
Not listed

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for DeepSeek V3.2
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding46.8Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic18.8Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning65.0Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning22.2Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning84.0Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding38.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning60.7Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath2.9Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)