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-Pro
Static closed-set multiple choice; contamination risk rises over time.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2024-06-03
- 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 8
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 | 84.0 | percent | EM | 2025-01-22 · document_publication | DeepSeek-R1 |
| DeepSeek-V3 | 75.9 | percent | EM, 8K output limit | 2024-12-27 · document_publication | DeepSeek-V3 |
| DeepSeek-V4-Pro | 82.9 | percent | non-think | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Pro | 87.1 | percent | think high | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Pro | 87.5 | percent | think max | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Flash | 87.5 | percent | think max | 2026-06-25 · document_publication | DeepSeek-V4 |
| Gemma 4 (31B) | 85.2 | percent | as reported | 2026-03-11 · document_publication | Gemma 4 (31B) |
| Qwen3.5-397B-A17B | 87.8 | percent | thinking (temp 0.6, top_p 0.95, top_k 20) | 2026-02-16 · document_publication | Qwen3.5-397B-A17B |