Model comparison
Amazon Nova Pro vs DeepSeek-V2.5 (Sep 2024)
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 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 1 category and DeepSeek-V2.5 (Sep 2024) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 35.9 to 28.5.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 31.0 | 37.6 |
| Released | 2024-12-03 | 2024-09-06 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 22 |
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-V2.5 (Sep 2024): 31.7 (#281)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Coding | 1270 | 1309 |
| Aider Polyglot | — | 17.8% |
| BigCodeBench Instruct | — | 48.6% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 53.2% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 74.1% |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 20.0 (#243), DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1289 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 28.5 (#243), DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Math | 1252 | 1288 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 27.4 (#250), DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Expert | 1211 | 1266 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), DeepSeek-V2.5 (Sep 2024): —
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 39.7 (#223), DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Non-English | 1234 | 1273 |
| LMArena Chinese | 1244 | 1318 |
| LMArena French | 1271 | 1289 |
| LMArena German | 1243 | 1258 |
| LMArena Japanese | 1200 | 1228 |
| LMArena Korean | 1203 | 1209 |
| LMArena Russian | 1240 | 1289 |
| LMArena Spanish | 1182 | 1248 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 64.9 (#226), DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Instruction Following | 1235 | 1280 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 38.1 (#205), DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Longer Query | 1255 | 1301 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
Amazon Nova Pro: 43.9 (#226), DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
| Benchmark | Amazon Nova Pro | DeepSeek-V2.5 (Sep 2024) |
|---|---|---|
| LMArena Text | 1259 | 1294 |
| LMArena Creative Writing | 1212 | 1285 |
| LMArena Multi-Turn | 1246 | 1297 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than DeepSeek-V2.5 (Sep 2024)?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or DeepSeek-V2.5 (Sep 2024) better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 31.7 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and DeepSeek-V2.5 (Sep 2024) share?
17 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and DeepSeek-V2.5 (Sep 2024) has 22.