We recognize the importance of
long-horizon execution for real-world tasks, where small per-step gains compound into much longer successful chains—so
Jan-v2-VL is built for stable, many-step execution. For evaluation, we use
The Illusion of Diminishing Returns: Measuring Long-Horizon Execution in LLMs, which measures execution length. This benchmark aligns with public consensus on what makes a strong coding model—steady, low-drift step execution—suggesting that robust long-horizon ability closely tracks better user experience.
Tasks where the plan and/or knowledge can be provided up front, and success hinges on stable, many-step execution with minimal drift:
Compared with its base (
Qwen-3-VL-8B-Thinking),
Jan-v2-VL shows
no degradation on standard text-only and vision tasks—and is
slightly better on several—while delivering stronger long-horizon execution on the
Illusion of Diminishing Returns benchmark.
Jan-v2-VL is optimized for direct integration with the
Jan App. Simply select the model from the Jan App interface for immediate access to its full capabilities.
1vllm serve Menlo/Jan-v2-VL-high \
2 --host 0.0.0.0 \
3 --port 1234 \
4 --enable-auto-tool-choice \
5 --tool-call-parser hermes \
6 --reasoning-parser qwen3
7
1llama-server --model Jan-v2-VL-high-Q8_0.gguf \
2 --vision-model-path mmproj-Jan-v2-VL-high.gguf \
3 --host 0.0.0.0 \
4 --port 1234 \
5 --jinja \
6 --no-context-shift
For optimal performance in agentic and general tasks, we recommend the following inference parameters:
1temperature: 1.0
2top_p: 0.95
3top_k: 20
4repetition_penalty: 1.0
5presence_penalty: 1.5
