Model comparison
Amazon Nova Experimental Chat 10 20 vs DeepSeek-V2.5 (Sep 2024)
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 8 categories and DeepSeek-V2.5 (Sep 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Amazon Nova Experimental Chat 10 20 leads 41.6 to 31.7.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 42.1 | 37.6 |
| Released | — | 2024-09-06 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 22 |
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: 41.6 (#123), DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Coding | 1412 | 1309 |
| Aider Polyglot | — | 17.8% |
| BigCodeBench Instruct | — | 48.6% |
| BigCodeBench Complete | — | 53.2% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Reasoning Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 28.4 (#106), DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1289 |
Math Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 39.0 (#119), DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1425 | 1288 |
Knowledge Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 38.5 (#144), DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1386 | 1266 |
Multilingual Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 49.5 (#131), DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1372 | 1273 |
| LMArena Chinese | 1404 | 1318 |
| LMArena French | 1425 | 1289 |
| LMArena German | 1391 | 1258 |
| LMArena Japanese | 1360 | 1228 |
| LMArena Korean | 1324 | 1209 |
| LMArena Russian | 1371 | 1289 |
| LMArena Spanish | 1382 | 1248 |
Instruction Following Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 72.1 (#141), DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1365 | 1280 |
Long Context Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 41.7 (#133), DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1370 | 1301 |
Writing & Preference Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 56.6 (#136), DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
| Benchmark | Amazon Nova Experimental Chat 10 20 | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1394 | 1294 |
| LMArena Creative Writing | 1318 | 1285 |
| LMArena Multi-Turn | 1364 | 1297 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 20 better than DeepSeek-V2.5 (Sep 2024)?
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 37.6 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 20 or DeepSeek-V2.5 (Sep 2024) better for coding?
Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 31.7 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 20 and DeepSeek-V2.5 (Sep 2024) share?
17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.