- AIME2025 (Avg@32) 78
- BFCL (Accuracy) 65
- ZebraLogic (Accuracy) 89.8
- MUSR (Accuracy) 86.7
- BBH (Accuracy) 87.8
- HumanEval+ (Pass@1) 90.8
- MBPP (Pass@1) 80.2
- IFEval (Prompt Strict Accuracy) 84.3
- Multi-IF (Accuracy) 63.3
- ChineseSimpleQA (Accuracy) 49.1
- WritingBench (critic-score, maximum 10) 8.65
ERNIE-4.5-21B-A3B-Thinking
ERNIE-4.5-21B-A3B-Thinking ranks first on MuSR.
12
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Baidu Sep 2025 ERNIE-4.5-21B-A3B-Thinking
Open weights Small
No Epoch Capabilities Index score yet
- AIME 2025 78% #93 /143
- IFEval 84.3% #81 /126
- Berkeley Function Calling Leaderboard (BFCL) 65% #33 /47
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 | |
|---|---|---|---|---|
| BIG-Bench Hard | 87.8% | #10 of 71 | Model card | |
| MuSR | 86.7% | #1 of 6 | Model card | |
| WritingBench | 8.65 | #5 of 14 | Model card | |
| IFEval | 84.3% | #81 of 126 | Model card | |
| Multi-IF | 63.3% | #21 of 28 | Model card | |
| Chinese SimpleQA | 49.1% | #13 of 13 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ZebraLogic | 89.8% | #5 of 23 | Model card | |
| AIME 2025 | 78% | #93 of 143 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MBPP | 80.2% | #20 of 66 | Model card | |
| HumanEval+ | 90.8% | #9 of 27 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 65% | #33 of 47 | Model card | |
| SnakeBench | 18 | #142 of 183 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.