DeepSeek Releases V4-Flash-Vision-Exp, First Multimodal Model in V4 Family
DeepSeek has released DeepSeek-V4-Flash-Vision-Exp, its first experimental multimodal model in the V4 family, adding visual understanding to the V4-Flash architecture. The 305B-parameter model shows substantial gains on multimodal agent benchmarks while holding steady on text-only tasks.
DeepSeek has released DeepSeek-V4-Flash-Vision-Exp, an experimental 305-billion-parameter model marking the first multimodal entry in its V4-Flash lineup. The model is available now on Hugging Face under the MIT License, though it is not yet deployed by any inference provider.
What's new
DeepSeek-V4-Flash-Vision-Exp builds on the existing DeepSeek-V4-Flash architecture by adding visual modules and undergoing continued training to enable image understanding. According to DeepSeek, the model achieves "substantial improvements" on multimodal agent tasks compared to its predecessor, DeepSeek-V4-Flash-0731, while keeping text-only agent performance roughly comparable.
The repository includes a tokenizer, a prompt-encoding reference supporting both OpenAI-style JSON content blocks and a compact <image>path</image> TXT notation, and a minimal PyTorch inference implementation. That implementation covers the vision encoder and aligner, DFlash attention, the mixture-of-experts (MoE) routing, Hyper-Connections, and the DSpark forward path. Model weights are distributed as safetensors in BF16, F32, F8_E4M3, I8, and I64 tensor formats.
Benchmark results
DeepSeek reports the following scores, comparing DeepSeek-V4-Flash-Vision-Exp against DeepSeek-V4-Flash-0731 and Anthropic's Opus-4.8, using DeepSeek Harness in minimal mode with maximum reasoning effort, temperature 1.0, and top_p 0.95:
Text agent capabilities:
- Terminal Bench 2.1: 83.9 vs. 82.7 (V4-Flash-0731) vs. 85.0 (Opus-4.8)
- NL2Repo: 57.7 vs. 54.2 vs. 69.7
- Cybergym: 75.3 vs. 76.7 vs. 78.3
- DeepSWE: 59.3 vs. 54.4 vs. 58.0
- Toolathlon-Verified: 75.9 vs. 70.3 vs. 76.2
- DSBench-Hard: 63.6 vs. 59.6 vs. 71.7
- AutomationBench (Public): 25.7 vs. 25.1 vs. 27.2
Multimodal agent capabilities:
- ApexBench (Pass@1): 36.5 vs. 26.2 vs. 39.4
- Agents' Last Exam: 27.3 vs. 25.2 vs. 25.7
- Chartography: 64.3 vs. not reported vs. 65.0
- ZeroBench (Pass@5): 35.0 vs. not reported vs. 34.0
DeepSeek notes that on ApexBench and Agents' Last Exam, the text-only V4-Flash-0731 baseline ignored multimodal elements in the input, which explains its lower scores on those tests.
On several multimodal benchmarks — ZeroBench and near-parity on Chartography and ApexBench — the new model closes much of the gap with Opus-4.8, a substantially larger and more established closed model. On text-only agent tasks, DeepSeek-V4-Flash-Vision-Exp trails Opus-4.8 on harder benchmarks like NL2Repo (57.7 vs. 69.7) and DSBench-Hard (63.6 vs. 71.7), but stays close on Terminal Bench 2.1 and Toolathlon-Verified.
No pricing has been disclosed, and the model is not yet available through any inference provider. Context window size was not specified in the release materials.
What this means
This is a research-stage, experimental release rather than a production-ready product — the "Exp" tag and lack of inference-provider deployment signal DeepSeek is testing the vision integration before a wider rollout. The architecture reuses V4-Flash's core components (DFlash attention, MoE, Hyper-Connections) rather than introducing a new base model, suggesting DeepSeek is incrementally extending its existing V4 line to multimodal use cases instead of training a separate vision-first model from scratch. The open MIT license and inclusion of a minimal PyTorch inference stack make it immediately usable for developers who want to experiment with DeepSeek's multimodal agent capabilities locally, ahead of any hosted API.
Related Articles
Meta Releases Muse Spark 1.3 Contributor, a Low-Cost Multimodal Reasoning Model With 1M Context Window
Meta has released Muse Spark 1.3 Contributor, described as the cost-efficient contributor tier of its multimodal reasoning model line. The model offers a 1 million token context window at $0.10 per 1M input tokens and $0.20 per 1M output tokens, targeting experimentation and early-stage agentic workflows.
Meta Releases Muse Spark 1.3, a Free Multimodal Reasoning Model with 1M-Token Context
Meta has released Muse Spark 1.3, a multimodal reasoning model with a 1M-token context window, listed as free on OpenRouter. The model targets long-running agentic, multi-agent, and coding workflows, though audio input support remains incomplete.
OpenAI's GPT-6 Astra Cuts Hallucinations, But Indirect Prompt Injection Attacks Still Succeed 8.5% of the Time
OpenAI's new GPT-6 Astra model shows major improvements in hallucination rates and jailbreak resistance over predecessor GPT-5.6 Sol, according to OpenAI's system card. However, indirect prompt injection attacks hidden in documents still succeed 8.5% of the time in external testing by Gray Swan, down from 27% but still above rival Claude Opus 5's 4.8% rate.
OpenAI Ships GPT-6 Astra, But Executives Admit They Can't Fully Monitor What It's Thinking
OpenAI released GPT-6 Astra on Thursday, a model president Greg Brockman says could mark the start of AGI. But the model writes out its reasoning less often than prior versions, and OpenAI's chief scientist says monitoring AI thought processes will keep getting harder.
Comments
Loading...