Mistral Nemo 12B Instruct
- Next shutdown
- None setNo date on 1 platform
- GPQA Diamond
- 29.9%#104 of 108 · Epoch AI
- Context window
- 128Ktokens
- Released
- Jul 18, 2024Mistral AI
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Mistral APIMistral AI: Models Overview (opens in a new tab) · checked Oct 14, 2026 | open-mistral-nemo-2407Shut down · also open-mistral-nemo | Shut down | Ministral 3 8B |
Mistral's models overview still showed the status Deprecated on 14 October 2026, after the retirement date.
What breaks when you move off Mistral Nemo 12B Instruct
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| GPQA Diamond | Epoch AI | 29.9% ± 2.1% | #104 of 108 | Jan 27, 2025 |
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
Change history
ShutdownDevstral 2, Magistral Medium 1.2 and Mistral Nemo retire from the Mistral APIMistral API1 break
devstral-2512, magistral-medium-2509 and open-mistral-nemo-2407 retired on 31 July 2026. Mistral names Mistral Medium 3.5 as the replacement for Devstral 2 and Magistral Medium 1.2, and Ministral 3 8B for Mistral Nemo.
- Platform
- Mistral API
- Announced
- BehaviorMagistral models always returned thinking traces. Mistral Small 4 and Mistral Medium 3.5 reason through the reasoning_effort parameter: high returns a thinking chunk before the answer, none omits it.
Source: Mistral AI, Models Overview (opens in a new tab); Mistral AI, Native reasoning (deprecated) (opens in a new tab); Mistral AI, Reasoning (opens in a new tab)