DeepSeek-V4-Flash-Vision-Exp Benchmark Details

DeepSeek-V4-Flash-Vision-Exp currently shows benchmark results led by Terminal-Bench 2.1 (11 / 44, score 83.90), NL2Repo-Bench (3 / 8, score 57.70), DeepSWE (12 / 27, score 59.30).

Benchmark Results

DeepSeek-V4-Flash-Vision-Exp

Benchmark Results

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 2.1

MaxTools

83.90

11 / 44

AutomationBench

MaxTools

25.70

7 / 8

Coding and Software Engineer

3 evaluations

Benchmark / mode

Score

Rank/total

DSBench-Hard

MaxTools

63.60

1 / 1

DeepSWE

MaxTools

59.30

12 / 27

NL2Repo-Bench

MaxTools

57.70

3 / 8

Agent Level Benchmark

2 evaluations

Benchmark / mode

Score

Rank/total

ApexBench

MaxTools

36.50

1 / 1

Agents' Last Exam

MaxTools

27.30

6 / 11

Multimodal Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

Chartography

MaxTools

64.30

1 / 1

ZeroBench Main

MaxTools

2 / 3

Compare with other models