IFEval (Mistral internal version)
Magistral Medium 1.0 87.4% Models follow prompts with verifiable format constraints. Mistral uses its own fixed version of IFEval.
Mistral says scores are not comparable with public IFEval scores.
- Made by
- Mistral AI
- Released
- June 2025
- Kind
- Following precise instructions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a launch post
- June 2025, dropped after it saturated
- Last model added
- June 2025
Magistral Medium 1.0 leads with 87.4%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Magistral Medium 1.0 87.4%
- 2 Mistral Small 3.2 84.8%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Magistral Medium 1.0 | 87.4% | Jun 2025 | Lab model card | |
| 2 | Mistral Small 3.2 | 84.8% | Jun 2025 | Lab model card |
Mistral AI’s own number for Magistral Medium 1.0 passed 85% in June 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs dropped it from launch posts once the best score passed 85%
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Jun 20, 2025 | Mistral Small 3.2 | 84.8 | IF (Internal; accuracy) |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jun 12, 2025 | Magistral Medium 1.0 technical report | 87.4 | Instruction following, IFEval internal version (Table 6) | Capabilities |
More in Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9% - IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose).
Nemotron-Cascade 2 30B-A3B 82.9% - MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85% - IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. Gemma 4 31B IT 95.9%