Model card
Mistral-Medium-3.
Mistralopen-source
§ 02 · Benchmarks
Every benchmark Mistral-Medium-3 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 62.0% | #60 | — | source ↗ |
| 02 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 78.0% | #66 | — | source ↗ |
| 03 | HLE | Reasoning · Multi-step Reasoning | accuracy | 4.5% | #69 | — | source ↗ |
| 04 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 77.0% | #71 | — | source ↗ |
| 05 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 67.0% | #72 | — | source ↗ |
| 06 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 66.8% | #73 | — | source ↗ |
| 07 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 56.0% | #74 | — | source ↗ |
| 08 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 61.0% | #80 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Mistral-Medium-3 actually performs.
§ 05 · Related models
Other Mistral models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
sdadas/PLCC
7
results
scale-hle-official
1
result
8 of 8 rows marked verified.