Model comparison
ERNIE 5.1 vs Mistral Small
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
Mistral AISummary
- They share 17 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Mistral Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where ERNIE 5.1 leads 40.3 to 16.4.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Mistral Small | |
|---|---|---|
| Provider | Baidu | Mistral AI |
| Noometry Index | 43.8 | 33.4 |
| Released | — | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 19 | 39 |
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), Mistral Small: 34.0 (#247)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Coding | 1488 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Mistral Small: 28.1 (#93)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| LMArena Search | 1227 | — |
Reasoning ERNIE 5.1 leads
ERNIE 5.1: 21.9 (#211), Mistral Small: 19.8 (#250)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 23.4% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Mistral Small: 16.4 (#293)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Math | 1481 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Mistral Small: 31.0 (#222)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Expert | 1492 | 1291 |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal Not comparable
ERNIE 5.1: —, Mistral Small: 33.5 (#96)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Mistral Small: 45.5 (#169)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1454 | 1315 |
| LMArena Chinese | 1508 | 1340 |
| LMArena French | 1488 | 1337 |
| LMArena German | 1470 | 1340 |
| LMArena Japanese | 1422 | 1275 |
| LMArena Korean | 1427 | 1259 |
| LMArena Russian | 1459 | 1324 |
| LMArena Spanish | 1473 | 1346 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Mistral Small: 66.4 (#209)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1460 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Mistral Small: 40.4 (#156)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1462 | 1327 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Mistral Small: 52.5 (#171)
| Benchmark | ERNIE 5.1 | Mistral Small |
|---|---|---|
| LMArena Text | 1468 | 1338 |
| LMArena Creative Writing | 1441 | 1305 |
| LMArena Multi-Turn | 1471 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is ERNIE 5.1 better than Mistral Small?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index.
Is ERNIE 5.1 or Mistral Small better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 34.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Mistral Small share?
17 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Mistral Small has 39.