Model comparison
Devstral Small 2505 vs ERNIE 5.0 0110
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
BaiduSummary
- The widest gap is in coding, where ERNIE 5.0 0110 leads 43.0 to 38.9.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | Mistral AI | Baidu |
| Noometry Index | 34.3 | 41.8 |
| 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 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
Devstral Small 2505: 38.9 (#166), ERNIE 5.0 0110: 43.0 (#94)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1455 |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), ERNIE 5.0 0110: 17.0 (#297)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 10.3% |
| CritPt | 0% | — |
| Thematic Generalization | — | 41.7% |
| LMArena Hard Prompts | — | 1445 |
Math Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 39.3 (#110)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | — | 1437 |
Knowledge Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 39.8 (#128)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | — | 1428 |
Multimodal Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 39.9 (#53)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1249 |
Multilingual Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 54.1 (#49)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | — | 1436 |
| LMArena Chinese | — | 1512 |
| LMArena French | — | 1467 |
| LMArena German | — | 1460 |
| LMArena Japanese | — | 1382 |
| LMArena Korean | — | 1406 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1473 |
Instruction Following Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 74.5 (#92)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | — | 1413 |
Long Context Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 43.4 (#95)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | — | 1422 |
Writing & Preference Not comparable
Devstral Small 2505: —, ERNIE 5.0 0110: 63.1 (#66)
| Benchmark | Devstral Small 2505 | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1426 |
| LMArena Multi-Turn | — | 1434 |
Frequently asked questions
Is Devstral Small 2505 better than ERNIE 5.0 0110?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or ERNIE 5.0 0110 better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 38.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and ERNIE 5.0 0110 share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and ERNIE 5.0 0110 has 20.