ERNIE 5.1
ERNIE 5.1 places in the top three on AIME 2026.
12
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Baidu May 2026 ERNIE 5.1
Closed weights Flagship
No Epoch Capabilities Index score yet
- MMLU-Pro 84.3% #39 /151
- DeepSearchQA 77.3% #16 /22
- tau3-bench 67.9% #7 /12
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 | |
|---|---|---|---|---|
| LMArena (Elo) | 1,467 | #41 of 333 | Official leaderboard | |
| MMLU-Pro | 84.3% | #39 of 151 | Model card | |
| AdvancedIF | 72.3% | #4 of 6 | Model card | |
| Extended NYT Connections | 23.4% | #81 of 97 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2026 | 99.6% | #2 of 34 | Model card | |
| GPQA Diamond | 91% | #21 of 284 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| tau3-bench | 67.9% | #7 of 12 | Model card | |
| LMArena Search Arena | 1,192 | #24 of 35 | Official leaderboard | |
| DeepSearchQA | 77.3% | #16 of 22 | Model card | |
| PACT | 1,485 | #22 of 26 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SpreadsheetBench Verified | 72.5% | #2 of 2 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SuperCLUE | 54.6 | #15 of 18 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.