Model comparison
Amazon Nova Experimental Chat 10 20 vs Devstral Small 2505
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 33.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where Amazon Nova Experimental Chat 10 20 leads 27.3 to 19.1.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 | |
|---|---|---|
| Provider | Amazon | Mistral AI |
| Noometry Index | 41.5 | 33.9 |
| Released | — | 2025-05-07 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 17 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 41.0 (#123), Devstral Small 2505: 38.6 (#160)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| LMArena Coding | 1413 | — |
Reasoning Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 27.3 (#110), Devstral Small 2505: 19.1 (#243)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | — | 37.7% |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1396 | — |
Math Not comparable
Amazon Nova Experimental Chat 10 20: 36.2 (#121), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Math | 1425 | — |
Knowledge Not comparable
Amazon Nova Experimental Chat 10 20: 37.8 (#142), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Expert | 1385 | — |
Multilingual Not comparable
Amazon Nova Experimental Chat 10 20: 49.7 (#127), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1405 | — |
| LMArena French | 1426 | — |
| LMArena German | 1391 | — |
| LMArena Japanese | 1355 | — |
| LMArena Korean | 1327 | — |
| LMArena Russian | 1371 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Not comparable
Amazon Nova Experimental Chat 10 20: 72.3 (#136), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Instruction Following | 1365 | — |
Long Context Not comparable
Amazon Nova Experimental Chat 10 20: 41.7 (#128), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Longer Query | 1370 | — |
Writing & Preference Not comparable
Amazon Nova Experimental Chat 10 20: 56.9 (#131), Devstral Small 2505: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | Devstral Small 2505 |
|---|---|---|
| LMArena Text | 1394 | — |
| LMArena Creative Writing | 1318 | — |
| LMArena Multi-Turn | 1364 | — |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 20 better than Devstral Small 2505?
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 41.5 to 33.9 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 20 or Devstral Small 2505 better for coding?
Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.0 versus 38.6 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 20 and Devstral Small 2505 share?
0 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Devstral Small 2505 has 4.