- AIME 2025 80.3
- MMLU-Pro 77
- IFBench 55.8
- Arena Hard v2 62.5
Solar Pro 3
Solar Pro 3.
6
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Upstage Jan 2026 Solar Pro 3
Closed weights
No Epoch Capabilities Index score yet
- IFBench 55.8% #60 /80
- MMLU-Pro 77% #101 /167
- AIME 2025 80.3% #88 /143
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU-Pro | 77% | #101 of 167 | Lab model card | |
| Arena-Hard v2.0 | 62.5% | #15 of 24 | Lab model card | |
| StudyArena Text | 1,217 | #58 of 85 | Official leaderboard | |
| IFBench | 55.8% | #60 of 80 | Lab model card | |
| Longform Creative Writing (EQ-Bench) | 27.0 | #116 of 119 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 80.3% | #88 of 143 | Lab model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.