evals.report
BenchmarksLabsCompareRun guidesIn the wild
DeepSeekDeepSeek-V4

DeepSeek V4 Flash 0731

DeepSeek · DeepSeek-V4. Released Jul 31, 2026.

DeepSeek V4 Flash 0731 is a model from DeepSeek in the DeepSeek-V4 family, released Jul 31, 2026. evals.report tracks 3 reported DeepSeek V4 Flash 0731 benchmark scores across DeepSWE, Terminal-Bench 2.1, Humanity's Last Exam — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

Open3 results

Benchmark results 3

Compare this model
BenchmarkCategoryScoreMetricStatusDate
DeepSWECoding54.4%% resolvedVerifiedJul 31, 2026Details
Terminal-Bench 2.1Agents82.7%task successVerifiedJul 31, 2026Details
Humanity's Last ExamReasoning37.8%accuracyVerifiedJul 31, 2026Details