Model comparison
Amazon Nova Micro vs Claude 3 Haiku
Amazon Nova Micro is the stronger model overall, scoring 30.4 to 25.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 7 categories and Claude 3 Haiku in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Micro leads 26.9 to 9.8.
Side by side
| Amazon Nova Micro | Claude 3 Haiku | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 30.4 | 25.9 |
| Released | 2024-12-03 | 2024-03-07 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Micro leads
Amazon Nova Micro: 30.5 (#295), Claude 3 Haiku: 26.4 (#325)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Coding | 1218 | 1199 |
| WeirdML | — | 9.8% |
| BigCodeBench Instruct | — | 39.4% |
| LiveBench Coding | 20.2% | — |
| BigCodeBench Complete | — | 50.1% |
| CadEval | — | 12% |
| HumanEval+ | — | 68.9% |
| MBPP+ | — | 68.8% |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), Claude 3 Haiku: —
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Claude 3 Haiku: 16.3 (#307)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1174 |
| Kagi LLM Benchmark | — | 34.2% |
| LiveBench Reasoning | 25.1% | — |
| DTBench | — | 50.1% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 118.35 |
| ForecastBench | — | 53.2 |
| LiveBench | 29.6% | — |
| WinoGrande | — | 74.2% |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), Claude 3 Haiku: 9.8 (#319)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Math | 1206 | 1188 |
| OTIS Mock AIME 2024-2025 | — | 1.8% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 14.9% |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.6 (#237), Claude 3 Haiku: 17.3 (#285)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Expert | 1184 | 1148 |
| MMLU | 70.8% | 73.8% |
| GPQA Diamond | — | 36.3% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 34.2% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Claude 3 Haiku: 23.6 (#128)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Vision | — | 950 |
| ScienceQA | — | 72% |
Multilingual Too close to call
Amazon Nova Micro: 36.5 (#239), Claude 3 Haiku: 36.0 (#243)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Non-English | 1186 | 1178 |
| LMArena Chinese | 1209 | 1155 |
| LMArena French | 1238 | 1195 |
| LMArena German | 1192 | 1174 |
| LMArena Japanese | 1154 | 1102 |
| LMArena Korean | 1150 | 1109 |
| LMArena Russian | 1185 | 1204 |
| LMArena Spanish | 1225 | 1166 |
Instruction Following Claude 3 Haiku leads
Amazon Nova Micro: 56.3 (#272), Claude 3 Haiku: 61.3 (#247)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Instruction Following | 1174 | 1173 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Too close to call
Amazon Nova Micro: 36.5 (#229), Claude 3 Haiku: 36.1 (#237)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Longer Query | 1205 | 1190 |
Writing & Preference Amazon Nova Micro leads
Amazon Nova Micro: 39.5 (#247), Claude 3 Haiku: 29.7 (#291)
| Benchmark | Amazon Nova Micro | Claude 3 Haiku |
|---|---|---|
| LMArena Text | 1208 | 1195 |
| LMArena Creative Writing | 1172 | 1157 |
| LMArena Multi-Turn | 1178 | 1190 |
| EQ-Bench Creative Writing | — | 717 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Claude 3 Haiku?
Amazon Nova Micro is the stronger model overall, scoring 30.4 to 25.9 on the Noometry Index.
Is Amazon Nova Micro or Claude 3 Haiku better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Claude 3 Haiku share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Claude 3 Haiku has 37.