Model comparison
Amazon Nova Experimental Chat 10 09 vs DeepSeek-V3.1
Amazon Nova Experimental Chat 10 09 and DeepSeek-V3.1 score almost the same on the Noometry Index (41.4 vs 42.2), so choose on price, context window or the category you care about most.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. Amazon Nova Experimental Chat 10 09 scores higher in 1 category and DeepSeek-V3.1 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 55.0.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 41.4 | 42.2 |
| Released | — | 2025-08-21 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.95 |
| Results tracked | 9 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Experimental Chat 10 09: 39.6 (#142), DeepSeek-V3.1: 39.8 (#140)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1371 | 1417 |
| WeirdML | — | 38.4% |
Reasoning DeepSeek-V3.1 leads
Amazon Nova Experimental Chat 10 09: 26.2 (#122), DeepSeek-V3.1: 27.3 (#109)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1417 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| DTBench | — | 82.7% |
| LMCA | — | 24.3% |
| Epoch Capabilities Index | — | 139.92 |
| ForecastBench | — | 58 |
Math Not comparable
Amazon Nova Experimental Chat 10 09: —, DeepSeek-V3.1: 36.1 (#125)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | — | 1420 |
Knowledge Not comparable
Amazon Nova Experimental Chat 10 09: —, DeepSeek-V3.1: 43.0 (#86)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1403 |
Multilingual DeepSeek-V3.1 leads
Amazon Nova Experimental Chat 10 09: 47.5 (#145), DeepSeek-V3.1: 51.8 (#100)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1341 | 1400 |
| LMArena Chinese | 1345 | 1470 |
| LMArena French | — | 1447 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1337 |
| LMArena Russian | — | 1405 |
| LMArena Spanish | — | 1429 |
Instruction Following DeepSeek-V3.1 leads
Amazon Nova Experimental Chat 10 09: 69.7 (#167), DeepSeek-V3.1: 74.1 (#105)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1316 | 1400 |
Long Context Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 40.6 (#146), DeepSeek-V3.1: 36.3 (#227)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1334 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference DeepSeek-V3.1 leads
Amazon Nova Experimental Chat 10 09: 55.0 (#144), DeepSeek-V3.1: 60.5 (#93)
| Benchmark | Amazon Nova Experimental Chat 10 09 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1365 | 1420 |
| LMArena Creative Writing | 1307 | 1401 |
| LMArena Multi-Turn | 1354 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 09 better than DeepSeek-V3.1?
Amazon Nova Experimental Chat 10 09 and DeepSeek-V3.1 score almost the same on the Noometry Index (41.4 vs 42.2), so choose on price, context window or the category you care about most.
Is Amazon Nova Experimental Chat 10 09 or DeepSeek-V3.1 better for coding?
They score almost the same on coding (39.6 vs 39.8); test both on your own repository before choosing.
How many benchmarks do Amazon Nova Experimental Chat 10 09 and DeepSeek-V3.1 share?
9 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 09 has 9 scored results on Noometry and DeepSeek-V3.1 has 27.