toolcompass.

Find your next AI tool

Search by product name or task. Press Escape to close.

← All model benchmarks

DeepSeek · LIVEBENCH 2026-06-25

DeepSeek V4 Flash Vision Exp

Published benchmark results for this specific model configuration.

deepseek-v4-flash-vision-exp
Overall score76.8 / 100
Cost / successful task$0.051USD · benchmark workload
Weight accessOpen weights

Where this configuration performs

Category averages from the same release, on a 0–100 scale.

Reasoning85.4
Coding68.2
Agentic Coding65.1
Mathematics87.8
Data Analysis79.5
Language80.4
Instruction Following71.0

Task-level results

theory of mind78.8zebra puzzle98.8spatial96.0logic with navigation68.0code generation69.0code completion67.4javascript63.6typescript56.7python75.0AMPS Hard88.0integrals with game76.0math comp97.1olympiad90.2consecutive events90.0tablejoin50.3tablereformat98.0connections99.3plot unscrambling57.7typos84.0paraphrase72.8simplify65.1story generation73.8summarize72.1

Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.