Model comparison
Amazon Nova Experimental Chat 26 02 10 vs DeepSeek-V3
Amazon Nova Experimental Chat 26 02 10 is the stronger model overall, scoring 44.5 to 39.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. Amazon Nova Experimental Chat 26 02 10 scores higher in 8 categories and DeepSeek-V3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Amazon Nova Experimental Chat 26 02 10 leads 44.0 to 34.0.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 44.5 | 39.5 |
| Released | — | 2024-12-26 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 164K |
| Input $ / M tokens | — | $0.24 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 12 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 43.9 (#82), DeepSeek-V3: 42.3 (#106)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Coding | 1483 | 1368 |
| Aider Polyglot | — | 55.1% |
| SciCode | — | 35.8% |
| WeirdML | — | 36.1% |
| BigCodeBench Instruct | — | 50% |
| LiveBench Coding | — | 70.9% |
| BigCodeBench Complete | — | 62.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73% |
Agentic & Tool Use Not comparable
Amazon Nova Experimental Chat 26 02 10: —, DeepSeek-V3: —
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| METR Time Horizons | — | 49.6% |
Reasoning Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 30.1 (#86), DeepSeek-V3: 20.5 (#236)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Hard Prompts | 1458 | 1365 |
| SimpleBench | — | 27.2% |
| Kagi LLM Benchmark | — | 52.3% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 65.8% |
| DTBench | — | 64.8% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 15.5% |
| BIG-Bench Hard | — | 87.5% |
| Epoch Capabilities Index | — | 135.94 |
| ForecastBench | — | 59.1 |
| HellaSwag | — | 88.9% |
| LiveBench | — | 66.9% |
| PIQA | — | 84.7% |
| WinoGrande | — | 85.2% |
Math Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 39.3 (#109), DeepSeek-V3: 32.1 (#219)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Math | 1438 | 1373 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| Omni-MATH | — | 40.3% |
| LiveBench Math | — | 73.5% |
| MATH Level 5 | — | 75.5% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 42.3 (#97), DeepSeek-V3: 37.5 (#155)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Expert | 1506 | 1351 |
| GPQA Diamond | — | 67.6% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 26.1% |
| Vectara Hallucination Rate | — | 6.1% |
| GPQA (HELM) | — | 53.8% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 87.2% |
| TriviaQA | — | 82.9% |
Multilingual Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 54.0 (#50), DeepSeek-V3: 48.5 (#143)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Non-English | 1434 | 1358 |
| LMArena Chinese | 1463 | 1391 |
| LMArena Russian | 1423 | 1373 |
| LMArena French | — | 1385 |
| LMArena German | — | 1374 |
| LMArena Japanese | — | 1333 |
| LMArena Korean | — | 1319 |
| LMArena Spanish | — | 1358 |
Instruction Following Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 75.2 (#69), DeepSeek-V3: 72.8 (#130)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Instruction Following | 1427 | 1345 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | — | 83.2% |
Long Context Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 44.0 (#77), DeepSeek-V3: 34.0 (#253)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Longer Query | 1441 | 1352 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Amazon Nova Experimental Chat 26 02 10 leads
Amazon Nova Experimental Chat 26 02 10: 61.8 (#84), DeepSeek-V3: 57.4 (#130)
| Benchmark | Amazon Nova Experimental Chat 26 02 10 | DeepSeek-V3 |
|---|---|---|
| LMArena Text | 1448 | 1375 |
| LMArena Creative Writing | 1368 | 1364 |
| LMArena Multi-Turn | 1442 | 1389 |
| Short-Story Creative Writing | — | 77% |
| EQ-Bench Creative Writing | — | 1472 |
| WildBench | — | 83% |
| LiveBench Language | — | 49.1% |
Frequently asked questions
Is Amazon Nova Experimental Chat 26 02 10 better than DeepSeek-V3?
Amazon Nova Experimental Chat 26 02 10 is the stronger model overall, scoring 44.5 to 39.5 on the Noometry Index.
Is Amazon Nova Experimental Chat 26 02 10 or DeepSeek-V3 better for coding?
Amazon Nova Experimental Chat 26 02 10 scores higher on coding benchmarks: 43.9 versus 42.3 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 26 02 10 and DeepSeek-V3 share?
12 benchmarks have published results for both models. Amazon Nova Experimental Chat 26 02 10 has 12 scored results on Noometry and DeepSeek-V3 has 60.