IFEval (Mistral internal version)
Magistral Medium 1.0 87.4% Dropped 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 Jun 2025 Following precise instructions Tasks kept private Last in a launch post Jun 2025 , dropped after it saturated
Last model added Jun 2025
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
2
Models scored in lab cards
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab
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%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Magistral Medium 1.0 | 87.4% | Jun 2025 | Model card | |
| 2 | Mistral Small 3.2 | 84.8% | Jun 2025 | Model card |
The best score passed 85% in Jun 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
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 |
|---|---|---|---|
| 20 Jun 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 |
|---|---|---|---|---|
| 12 Jun 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. LFM3-1.7B 93.7%