BenchLM is tracking Mistral Small 4 (Reasoning) by Mistral. Some benchmark data is visible, but trusted coverage is not complete enough for ranking yet.
BenchLM is tracking Mistral Small 4 (Reasoning), but this profile is currently excluded from the trusted leaderboard because its source-backed benchmark coverage is not complete enough yet. We keep the model metadata and any verified benchmark rows visible while the rest of the public eval record is re-checked.
Mistral Small 4 (Reasoning) is a open weight model with a 256K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.
Mistral Small 4 (Reasoning) sits inside the Mistral Small 4 family alongside Mistral Small 4. This profile currently has 2 trusted benchmark rows on BenchLM, but that is not enough for a leaderboard rank yet.
Creator
Mistral
Source Type
Open WeightReasoning
ReasoningContext Window
256K
Overall Score
Not ranked yet
BenchLM is still verifying enough trusted benchmark coverage to place this model in the leaderboard. Category ranks will appear here once that source-backed coverage is complete.
BenchLM is tracking Mistral Small 4 (Reasoning), but trusted source-backed benchmark coverage is still coming soon. We currently list its creator, model type, and context window while we wait for verified public benchmark results.
Yes, Mistral Small 4 (Reasoning) is an open weight model created by Mistral, meaning it can be downloaded and run locally or fine-tuned for specific use cases.
Mistral Small 4 (Reasoning) belongs to the Mistral Small 4 family. Related variants on BenchLM include Mistral Small 4.
Mistral Small 4 (Reasoning) is tracked on BenchLM, but its current source-backed benchmark coverage is not strong enough for a trusted leaderboard rank yet. We keep the model page live while we verify more public benchmark results.
Mistral Small 4 (Reasoning) has a context window of 256K, which determines how much text it can process in a single interaction.
New model releases, benchmark scores, and leaderboard changes. Every Friday.
Free. Your signup is stored with a derived country code for compliance routing.