Model record

DeepSeek V4 Flash

maxOpen weights

DeepSeek · released Apr 24, 2026

Overall standing

Overall
50.0rank 29 of 63
50.0 is at approximately the 55th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
8 of 8 measured
Category standingsReasoning 65.9Coding 53.4Math 7.1Agentic 22.9
Reasoning
65.9rank 26 of 63
65.9 is at approximately the 60th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
4 of 4 measured
Coding
53.4rank 34 of 63
53.4 is at approximately the 47th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
2 of 2 measured
Math
7.1rank 30 of 63
7.1 is at approximately the 53th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.7.
1 of 1 measured
Agentic
22.9rank 24 of 63
22.9 is at approximately the 63th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
1 of 1 measured
Model factsOpen weights · $0.14 / $0.28 per 1M

Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.

Provider
DeepSeek
Released
Weights
Open weights
Context window
1,000,000 tokens
Input price / Mtok
$0.14
Output price / Mtok
$0.28
Price source
Official pricing (opens in a new tab)
Reasoning effort
reasoning, max effort

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 V4 Flash
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding61.8Artificial 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-BankingAgentic22.9Artificial 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-LCRReasoning63.0Artificial 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 ExamReasoning32.1Artificial 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 DiamondReasoning89.4Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding44.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning79.2Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath7.1Artificial 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)