Model comparison
Amazon Nova Pro vs DeepSeek LLM 67B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and DeepSeek LLM 67B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Pro leads 27.4 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 31.0 | 24.9 |
| Released | 2024-12-03 | 2023-11-29 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1270 | 1096 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), DeepSeek LLM 67B: —
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1070 |
| Epoch Capabilities Index | 123.8 | 110.5 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1252 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 6.4% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| LMArena Expert | 1211 | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), DeepSeek LLM 67B: —
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1234 | 1073 |
| LMArena Chinese | 1244 | 1132 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1240 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1079 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1255 | 1092 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Amazon Nova Pro | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1259 | 1105 |
| LMArena Creative Writing | 1212 | 1067 |
| LMArena Multi-Turn | 1246 | 1082 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than DeepSeek LLM 67B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 24.9 on the Noometry Index.
Is Amazon Nova Pro or DeepSeek LLM 67B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 31.9 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and DeepSeek LLM 67B share?
11 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and DeepSeek LLM 67B has 15.