AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
MMLU
Saturated at the frontier and heavily contaminated. Useful as a historical baseline, not as a ranking signal.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2020-09-07
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 4
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| DeepSeek-R1 | 90.8 | percent | EM | 2025-01-22 · document_publication | DeepSeek-R1 |
| DeepSeek-V3 | 88.5 | percent | EM, 8K output limit | 2024-12-27 · document_publication | DeepSeek-V3 |
| Gemini 1.5 Pro | 85.9 | percent | 5-shot | 2024-03-08 · document_publication | Gemini 1.5 |
| Mistral Large 2 | 84.0 | percent | pretrained | 2024-07-24 · document_publication | Mistral Large 2 |