Doubao-1.5-pro
Doubao-1.5-pro ranks first on 2 of the 12 benchmarks with five or more models scored.
ByteDance Seed Released January 22nd, 2025 Family Doubao 1.5 The lab's model card Compare with others 12
Benchmarks with a score
2
Ranked first, out of five or more models
3
In the top three
ByteDance Seed Jan 2025 Doubao-1.5-pro
Closed weights Flagship
No Epoch Capabilities Index score yet
- MARS-Bench 52.6% #4 /15
- Multi-SWE-bench mini 4.50% #5 /5
- CharXiv (DQ) 84.3% #11 /67
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 | |
|---|---|---|---|---|
| Role-play Benchmark (MiniMax) | 80.6 | #1 of 8 | Official leaderboard | |
| MARS-Bench | 52.6% | #4 of 15 | Official leaderboard | |
| MMLU-Pro | 80.1% | #57 of 212 | Official leaderboard | |
| SuperGPQA | 50.9% | #21 of 59 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Multi-SWE-bench | 2.57% | #11 of 11 | Official leaderboard | |
| Multi-SWE-bench mini | 4.50% | #5 of 5 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MathVista | 79.5% | #1 of 43 | Official leaderboard | |
| We-Math | 65.7% | #2 of 21 | Official leaderboard | |
| CharXiv | 54.4% | #9 of 77 | Official leaderboard | |
| CharXiv (DQ) | 84.3% | #11 of 67 | Official leaderboard | |
| MMSI-Bench | 33% | #5 of 28 | Official leaderboard | |
| MATH-Vision (MathVision) | 48.6% | #53 of 105 | Official leaderboard |