Model comparison
ERNIE 5.1 vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Baidu
GoogleSummary
- They share 19 benchmarks with published results for both. ERNIE 5.1 scores higher in 2 categories and Gemini 3 Flash Preview in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 21.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 83.1% for Gemini 3 Flash Preview.
Side by side
| ERNIE 5.1 | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | Baidu | |
| Noometry Index | 43.8 | 52.3 |
| Released | — | 2025-12-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 19 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
ERNIE 5.1: 44.0 (#76), Gemini 3 Flash Preview: 50.9 (#42)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Coding | 1488 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| WeirdML | — | 61.6% |
| ALE-Bench | — | 1,367 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Gemini 3 Flash Preview: 38.7 (#29)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Search | 1227 | 1198 |
| Terminal-Bench | — | 64.3% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
ERNIE 5.1: 21.9 (#211), Gemini 3 Flash Preview: 49.2 (#37)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| NYT Connections (extended) | 23.4% | 83.1% |
| LMArena Hard Prompts | 1481 | 1465 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 89.1% |
| LMCA | — | 43.1% |
| Epoch Capabilities Index | — | 151.8 |
| ForecastBench | — | 58.5 |
Math Gemini 3 Flash Preview leads
ERNIE 5.1: 40.3 (#92), Gemini 3 Flash Preview: 51.7 (#55)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Math | 1481 | 1473 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 15% |
| FrontierMath (Feb 2025 set) | — | 35.6% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 3 Flash Preview leads
ERNIE 5.1: 41.9 (#102), Gemini 3 Flash Preview: 58.8 (#33)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Expert | 1492 | 1462 |
| GPQA Diamond | — | 89.4% |
| SimpleQA Verified | — | 66.8% |
| Vectara Hallucination Rate | — | 13.5% |
Multimodal Not comparable
ERNIE 5.1: —, Gemini 3 Flash Preview: 45.5 (#16)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | — | 1285 |
| GeoBench | — | 88% |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
Multilingual Too close to call
ERNIE 5.1: 55.5 (#29), Gemini 3 Flash Preview: 55.7 (#27)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1454 | 1458 |
| LMArena Chinese | 1508 | 1511 |
| LMArena French | 1488 | 1477 |
| LMArena German | 1470 | 1497 |
| LMArena Japanese | 1422 | 1489 |
| LMArena Korean | 1427 | 1443 |
| LMArena Russian | 1459 | 1480 |
| LMArena Spanish | 1473 | 1469 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Gemini 3 Flash Preview: 75.7 (#56)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1460 | 1437 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), Gemini 3 Flash Preview: 44.4 (#67)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1462 | 1452 |
Writing & Preference Too close to call
ERNIE 5.1: 65.1 (#52), Gemini 3 Flash Preview: 65.5 (#45)
| Benchmark | ERNIE 5.1 | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1468 | 1466 |
| LMArena Creative Writing | 1441 | 1457 |
| LMArena Multi-Turn | 1471 | 1471 |
Frequently asked questions
Is ERNIE 5.1 better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 43.8 on the Noometry Index.
Is ERNIE 5.1 or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Gemini 3 Flash Preview share?
19 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Gemini 3 Flash Preview has 59.