Model comparison
Amazon Nova Pro vs Claude 3.5 Haiku
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.2 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Amazon Nova Pro scores higher in 6 categories and Claude 3.5 Haiku in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 14.7.
- The biggest single-benchmark swing is LiveBench Coding: 38.1% for Amazon Nova Pro and 51.4% for Claude 3.5 Haiku.
Side by side
| Amazon Nova Pro | Claude 3.5 Haiku | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 31.0 | 29.2 |
| Released | 2024-12-03 | 2024-10-22 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 49 |
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 3.5 Haiku: 32.9 (#265)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Coding | 38.1% | 51.4% |
| LMArena Coding | 1270 | 1286 |
| Aider Polyglot | — | 28% |
| SciCode | — | 27.4% |
| WeirdML | — | 30.7% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 59% |
| CadEval | — | 32% |
Agentic & Tool Use Claude 3.5 Haiku leads
Amazon Nova Pro: 16.7 (#147), Claude 3.5 Haiku: 28.0 (#95)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 19.3% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Claude 3.5 Haiku: 17.7 (#290)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Reasoning | 32.6% | 28.1% |
| LMArena Hard Prompts | 1246 | 1251 |
| LiveBench Data Analysis | 48.3% | 48.5% |
| Epoch Capabilities Index | 123.8 | 127.15 |
| LiveBench | 43.5% | 43.5% |
| CritPt | — | 0% |
| DTBench | — | 56.7% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Claude 3.5 Haiku: 14.7 (#300)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| Omni-MATH | 24.2% | 22.4% |
| LiveBench Math | 38% | 35.5% |
| LMArena Math | 1252 | 1244 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 46.4% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Claude 3.5 Haiku: 18.7 (#281)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| MMLU-Pro | 67.3% | 60.5% |
| Confabulations | 30.1% | 36.7% |
| GPQA (HELM) | 44.6% | 36.3% |
| LMArena Expert | 1211 | 1208 |
| MMLU | 82% | 74.3% |
| GPQA Diamond | — | 38.1% |
| Humanity's Last Exam | 4.4% | — |
| Vectara Hallucination Rate | 5.1% | — |
Multimodal Claude 3.5 Haiku leads
Amazon Nova Pro: 25.0 (#126), Claude 3.5 Haiku: 26.8 (#117)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LMArena Vision | 980 | 1092 |
| GeoBench | — | 34% |
Multilingual Too close to call
Amazon Nova Pro: 39.7 (#223), Claude 3.5 Haiku: 40.0 (#218)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LMArena Non-English | 1234 | 1238 |
| LMArena Chinese | 1244 | 1229 |
| LMArena French | 1271 | 1264 |
| LMArena German | 1243 | 1237 |
| LMArena Japanese | 1200 | 1175 |
| LMArena Korean | 1203 | 1173 |
| LMArena Russian | 1240 | 1253 |
| LMArena Spanish | 1182 | 1261 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Claude 3.5 Haiku: 62.9 (#234)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 61.9% |
| IFEval | 81.5% | 79.2% |
| LMArena Instruction Following | 1235 | 1241 |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), Claude 3.5 Haiku: 38.3 (#200)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LMArena Longer Query | 1255 | 1261 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Claude 3.5 Haiku: 42.7 (#234)
| Benchmark | Amazon Nova Pro | Claude 3.5 Haiku |
|---|---|---|
| LMArena Text | 1259 | 1255 |
| LMArena Creative Writing | 1212 | 1233 |
| Short-Story Creative Writing | 60.5% | 73.5% |
| WildBench | 77.7% | 76% |
| LMArena Multi-Turn | 1246 | 1265 |
| LiveBench Language | 37% | 35.4% |
| EQ-Bench Creative Writing | — | 1146 |
Frequently asked questions
Is Amazon Nova Pro better than Claude 3.5 Haiku?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.2 on the Noometry Index.
Is Amazon Nova Pro or Claude 3.5 Haiku 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 3.5 Haiku share?
34 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude 3.5 Haiku has 49.