Leaderboard bars
1 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Mistral Large 3 | #1 | Mistral AI | 55.1% |
Loading benchmark header
Loading benchmark registry
Instruction Following · Benchmark profile
An automated pairwise evaluation set derived from challenging user prompts.
Data verified 15 July 2026 · Methodology 1.2.0
Visual analysis
Three views of the same sourced leaderboard: model placement, the score curve, and descriptive provider averages. These visuals never alter ranking calculations.
1 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Mistral Large 3 | #1 | Mistral AI | 55.1% |
Shows how quickly scores separate down the field
| Model | Rank | Provider | Score |
|---|---|---|---|
| Mistral Large 3 | #1 | Mistral AI | 55.1% |
Average within the visible cohort · descriptive only
| Provider | Models | Average score |
|---|---|---|
| Mistral AI | 1 | 55.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Score |
|---|---|---|---|---|
| #1 | Mistral Large 3 mistral-large-2512 | Mistral AI | open | 55.1% |
About Arena-Hard-Auto
An automated pairwise evaluation set derived from challenging user prompts. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
An automated pairwise evaluation set derived from challenging user prompts.
Mistral Large 3 by Mistral AI currently leads with 55.1%.
1 model in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related