Mistral
availableShows if the model has enough results for an index.Mistral Large 4
Mistral Large 4 is a reasoning model from Mistral. 16 benchmarks count toward its index, in 6 categories.
IndexOverall score out of 100.62.1±5.0Median 50.7
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.116/sMedian 62/s
First tokenSeconds to the first output token.18.7 sMedian 1.6 s
Input / 1MUS dollars per 1M input tokens.$0.68Median $0.6
Output / 1MUS dollars per 1M output tokens.$2.09Median $2.5
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.N/AMedian 1427
Capabilities
Score per category, out of 100.Results
16 countedBenchmarkThe test name.ResultThe score from the source.PlacePlace among results on this benchmark.