Model comparison
ERNIE 5.1 vs Gemma 3 27B
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
GoogleSummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Gemma 3 27B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where ERNIE 5.1 leads 44.0 to 22.5.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Gemma 3 27B | |
|---|---|---|
| Provider | Baidu | |
| Noometry Index | 43.8 | 30.8 |
| Released | — | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 19 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), Gemma 3 27B: 22.5 (#334)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1488 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| LiveBench Coding | — | 39.9% |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Gemma 3 27B: 25.1 (#110)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Gemma 3 27B: 16.7 (#301)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1340 |
| Kagi LLM Benchmark | — | 40.4% |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 51.5% |
| LMCA | — | 12.3% |
| Epoch Capabilities Index | — | 130.04 |
| LiveBench | — | 50% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Gemma 3 27B: 25.9 (#265)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1481 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Gemma 3 27B: 25.5 (#261)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Expert | 1492 | 1304 |
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
ERNIE 5.1: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Gemma 3 27B: 46.9 (#155)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1454 | 1334 |
| LMArena Chinese | 1508 | 1346 |
| LMArena French | 1488 | 1368 |
| LMArena German | 1470 | 1362 |
| LMArena Japanese | 1422 | 1287 |
| LMArena Korean | 1427 | 1308 |
| LMArena Russian | 1459 | 1349 |
| LMArena Spanish | 1473 | 1349 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Gemma 3 27B: 70.6 (#160)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1460 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Gemma 3 27B: 27.6 (#293)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1462 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Gemma 3 27B: 52.5 (#168)
| Benchmark | ERNIE 5.1 | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1468 | 1358 |
| LMArena Creative Writing | 1441 | 1346 |
| LMArena Multi-Turn | 1471 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is ERNIE 5.1 better than Gemma 3 27B?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 30.8 on the Noometry Index.
Is ERNIE 5.1 or Gemma 3 27B better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 22.5 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Gemma 3 27B share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemma 3 27B has 43.