Model comparison
Devstral Small 2505 vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
BaiduSummary
- The widest gap is in coding, where ERNIE 5.1 leads 44.0 to 38.9.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | ERNIE 5.1 | |
|---|---|---|
| Provider | Mistral AI | Baidu |
| Noometry Index | 34.3 | 43.8 |
| Released | 2025-05-07 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
Devstral Small 2505: 38.9 (#166), ERNIE 5.1: 44.0 (#76)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1488 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, ERNIE 5.1: —
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning ERNIE 5.1 leads
Devstral Small 2505: 19.7 (#252), ERNIE 5.1: 21.9 (#211)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 23.4% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1481 |
Math Not comparable
Devstral Small 2505: —, ERNIE 5.1: 40.3 (#92)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Math | — | 1481 |
Knowledge Not comparable
Devstral Small 2505: —, ERNIE 5.1: 41.9 (#102)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | — | 1492 |
Multilingual Not comparable
Devstral Small 2505: —, ERNIE 5.1: 55.5 (#29)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | — | 1454 |
| LMArena Chinese | — | 1508 |
| LMArena French | — | 1488 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1459 |
| LMArena Spanish | — | 1473 |
Instruction Following Not comparable
Devstral Small 2505: —, ERNIE 5.1: 76.7 (#37)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | — | 1460 |
Long Context Not comparable
Devstral Small 2505: —, ERNIE 5.1: 44.7 (#59)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | — | 1462 |
Writing & Preference Not comparable
Devstral Small 2505: —, ERNIE 5.1: 65.1 (#52)
| Benchmark | Devstral Small 2505 | ERNIE 5.1 |
|---|---|---|
| LMArena Text | — | 1468 |
| LMArena Creative Writing | — | 1441 |
| LMArena Multi-Turn | — | 1471 |
Frequently asked questions
Is Devstral Small 2505 better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 38.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and ERNIE 5.1 share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and ERNIE 5.1 has 19.