Decision modelOpen source
Intern-Decision-0.8B
InternLM
- Released
- -
- Data date
- October 3, 2026
Intern-Decision-0.8B is the smallest model in the multimodal Intern-Decision line. It accepts shared state, named questions, and optional images. One forward pass produces typed JSON answers with Choice, Score, and Noul probabilities. The runtime does not call free-text generation.
The 0.8-billion-parameter checkpoint is fine-tuned from Qwen3.5-0.8B. Apache-2.0 weights run locally with the bundled DecisionEngine and have an 8,192-token input limit.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Multimodal structured decision model, not a free-text generatorSource |
| Output schema | Choice, Score, and Noul as typed JSON answers with probabilitiesSource |
| Input | State, named questions, and optional imagesSource |
| Access | Local Hugging Face execution with the bundled DecisionEngineSource |
| Checkpoint | internlm/Intern-Decision-0.8BSource |
| Base model | Qwen/Qwen3.5-0.8BSource |
| Context window | 8,192-token runtime input limitSource |
| License | Apache-2.0 with the Qwen notices retainedSource |
Page 1 of 2
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Intern Decision evaluation: Jevbench-Easy (Show measurement, test conditions, and source)
- Source value
- 97.92
- Score
- 97.92
- Metric
- Jevbench-Easy
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: Jevbench-Original (Show measurement, test conditions, and source)
- Source value
- 80.56
- Score
- 80.56
- Metric
- Jevbench-Original
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: Jevbench-Hard (Show measurement, test conditions, and source)
- Source value
- 52.25
- Score
- 52.25
- Metric
- Jevbench-Hard
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: Typed Decision (Show measurement, test conditions, and source)
- Source value
- 77.35
- Score
- 77.35
- Metric
- Typed Decision
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: ToolACE (Show measurement, test conditions, and source)
- Source value
- 94.52
- Score
- 94.52
- Metric
- ToolACE
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: AG News (Show measurement, test conditions, and source)
- Source value
- 88.61
- Score
- 88.61
- Metric
- AG News
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: WildJailBreak (Show measurement, test conditions, and source)
- Source value
- 64.48
- Score
- 64.48
- Metric
- WildJailBreak
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: Average (Show measurement, test conditions, and source)
- Source value
- 79.38
- Score
- 79.38
- Metric
- Average
- Unit
- %
- Category
- Intern Decision evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: Brier (Show measurement, test conditions, and source)
- Source value
- 0.53
- Score
- 0.53
- Metric
- Brier
- Unit
- ratio
- Category
- Intern Decision evaluation
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision evaluation: ECE (Show measurement, test conditions, and source)
- Source value
- 0.066
- Score
- 0.066
- Metric
- ECE
- Unit
- ratio
- Category
- Intern Decision evaluation
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Local Hugging Face inference=yes; Structured candidate scoring=yes
Intern Decision inference latency: Mean (seconds) (Show measurement, test conditions, and source)
- Source value
- 0.03398
- Score
- 0.03398
- Metric
- Mean
- Unit
- seconds
- Category
- Intern Decision inference latency
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Hardware=Single RTX 4090; Inference path=local HF; Time definition=Per-query end-to-end latency
Intern Decision inference latency: Median / P50 (seconds) (Show measurement, test conditions, and source)
- Source value
- 0.03344
- Score
- 0.03344
- Metric
- Median / P50
- Unit
- seconds
- Category
- Intern Decision inference latency
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- InternLM Intern-Decision-0.8B model card
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Hardware=Single RTX 4090; Inference path=local HF; Time definition=Per-query end-to-end latency
Page 1 of 2
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | Intern-Decision collection (retrieved October 3, 2026) · Intern-Decision collection · Editorial description reviewed October 3, 2026 |
| Additional source | Intern-Decision repository (retrieved October 3, 2026) · Intern-Decision repository · Editorial description reviewed October 3, 2026 |
| Additional source | Intern-Decision-0.8B model card (retrieved October 3, 2026; October 4, 2026) · Intern-Decision-0.8B model card · Editorial description reviewed October 3, 2026 |