Model comparison
Amazon Nova Pro vs Deepseek Coder v2
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 categories and Deepseek Coder v2 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 28.5.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Deepseek Coder v2 | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 31.0 | 35.9 |
| Released | 2024-12-03 | 2024-06-17 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Amazon Nova Pro: 35.1 (#229), Deepseek Coder v2: 38.1 (#183)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Coding | 1270 | 1251 |
| BigCodeBench Instruct | — | 48.2% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 59.7% |
| HumanEval+ | — | 82.3% |
| MBPP+ | — | 75.1% |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Deepseek Coder v2: —
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Deepseek Coder v2 leads
Amazon Nova Pro: 20.0 (#243), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1207 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
| WinoGrande | — | 83.7% |
Math Deepseek Coder v2 leads
Amazon Nova Pro: 28.5 (#243), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1252 | 1241 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| GSM8K | — | 94.5% |
Knowledge Deepseek Coder v2 leads
Amazon Nova Pro: 27.4 (#250), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1211 | 1181 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| ARC (AI2) Challenge | — | 64.3% |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Deepseek Coder v2: —
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Deepseek Coder v2: 36.3 (#240)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1234 | 1182 |
| LMArena Chinese | 1244 | 1201 |
| LMArena French | 1271 | 1185 |
| LMArena German | 1243 | 1164 |
| LMArena Japanese | 1200 | 1126 |
| LMArena Korean | 1203 | 1104 |
| LMArena Russian | 1240 | 1188 |
| LMArena Spanish | 1182 | 1153 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Deepseek Coder v2: 61.7 (#242)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1180 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Deepseek Coder v2: 37.0 (#224)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1255 | 1219 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Deepseek Coder v2: 38.2 (#253)
| Benchmark | Amazon Nova Pro | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1259 | 1191 |
| LMArena Creative Writing | 1212 | 1120 |
| LMArena Multi-Turn | 1246 | 1177 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Deepseek Coder v2?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 35.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Deepseek Coder v2 share?
17 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Deepseek Coder v2 has 24.