Model comparison
Amazon Nova Pro vs Claude 3 Opus
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Amazon Nova Pro scores higher in 5 categories and Claude 3 Opus in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 14.8.
- The biggest single-benchmark swing is LiveBench Language: 37% for Amazon Nova Pro and 50.4% for Claude 3 Opus.
Side by side
| Amazon Nova Pro | Claude 3 Opus | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 29.5 |
| Released | 2024-12-03 | 2024-02-29 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 46 |
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), Claude 3 Opus: 32.9 (#267)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LiveBench Coding | 38.1% | 38.6% |
| LMArena Coding | 1270 | 1264 |
| WeirdML | — | 19.2% |
| BigCodeBench Instruct | — | 45.5% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 77.4% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Claude 3 Opus leads
Amazon Nova Pro: 16.7 (#147), Claude 3 Opus: 24.6 (#116)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 29.5% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Claude 3 Opus: 14.6 (#324)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LiveBench Reasoning | 32.6% | 40.6% |
| LMArena Hard Prompts | 1246 | 1245 |
| LiveBench Data Analysis | 48.3% | 57.9% |
| Epoch Capabilities Index | 123.8 | 126.91 |
| LiveBench | 43.5% | 49.2% |
| SimpleBench | — | 23.5% |
| Chess Puzzles | — | 5% |
| EnigmaEval | — | 0.8% |
| DTBench | — | 61.6% |
| LMCA | — | 17% |
| ForecastBench | — | 58.4 |
| WinoGrande | — | 88.5% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Claude 3 Opus: 14.8 (#299)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LiveBench Math | 38% | 43.6% |
| LMArena Math | 1252 | 1273 |
| OTIS Mock AIME 2024-2025 | — | 4.7% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 37.5% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Claude 3 Opus: 24.5 (#267)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| Confabulations | 30.1% | 22.7% |
| LMArena Expert | 1211 | 1223 |
| MMLU | 82% | 84.6% |
| GPQA Diamond | — | 47.2% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 12.6% |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
Multimodal Claude 3 Opus leads
Amazon Nova Pro: 25.0 (#126), Claude 3 Opus: 27.1 (#116)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LMArena Vision | 980 | 1023 |
Multilingual Claude 3 Opus leads
Amazon Nova Pro: 39.7 (#223), Claude 3 Opus: 41.4 (#207)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LMArena Non-English | 1234 | 1258 |
| LMArena Chinese | 1244 | 1248 |
| LMArena French | 1271 | 1275 |
| LMArena German | 1243 | 1258 |
| LMArena Japanese | 1200 | 1204 |
| LMArena Korean | 1203 | 1187 |
| LMArena Russian | 1240 | 1280 |
| LMArena Spanish | 1182 | 1246 |
Instruction Following Too close to call
Amazon Nova Pro: 64.9 (#226), Claude 3 Opus: 64.1 (#228)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 63.9% |
| LMArena Instruction Following | 1235 | 1248 |
| IFEval | 81.5% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), Claude 3 Opus: 38.2 (#202)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LMArena Longer Query | 1255 | 1259 |
Writing & Preference Claude 3 Opus leads
Amazon Nova Pro: 43.9 (#226), Claude 3 Opus: 47.2 (#213)
| Benchmark | Amazon Nova Pro | Claude 3 Opus |
|---|---|---|
| LMArena Text | 1259 | 1262 |
| LMArena Creative Writing | 1212 | 1235 |
| LMArena Multi-Turn | 1246 | 1275 |
| LiveBench Language | 37% | 50.4% |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Claude 3 Opus?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.5 on the Noometry Index.
Is Amazon Nova Pro or Claude 3 Opus better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 32.9 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Claude 3 Opus share?
28 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude 3 Opus has 46.