Model comparison
Amazon Nova Micro vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Yi-Lightning leads 67.4 to 56.3.
Side by side
| Amazon Nova Micro | Yi-Lightning | |
|---|---|---|
| Provider | Amazon | 01.AI |
| Noometry Index | 30.4 | 37.1 |
| Released | 2024-12-03 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 18 |
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), Yi-Lightning: 27.4 (#320)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1218 | 1312 |
| Aider Polyglot | — | 12.9% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), Yi-Lightning: —
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Yi-Lightning leads
Amazon Nova Micro: 17.4 (#294), Yi-Lightning: 25.9 (#139)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1302 |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| LiveBench | 29.6% | — |
Math Yi-Lightning leads
Amazon Nova Micro: 26.9 (#254), Yi-Lightning: 36.2 (#172)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Math | 1206 | 1300 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Yi-Lightning leads
Amazon Nova Micro: 29.6 (#237), Yi-Lightning: 35.4 (#185)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1184 | 1286 |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual Yi-Lightning leads
Amazon Nova Micro: 36.5 (#239), Yi-Lightning: 42.2 (#196)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1186 | 1269 |
| LMArena Chinese | 1209 | 1320 |
| LMArena French | 1238 | 1305 |
| LMArena German | 1192 | 1267 |
| LMArena Japanese | 1154 | 1228 |
| LMArena Korean | 1150 | 1192 |
| LMArena Russian | 1185 | 1255 |
| LMArena Spanish | 1225 | 1315 |
Instruction Following Yi-Lightning leads
Amazon Nova Micro: 56.3 (#272), Yi-Lightning: 67.4 (#196)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1174 | 1278 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Yi-Lightning leads
Amazon Nova Micro: 36.5 (#229), Yi-Lightning: 39.4 (#181)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1205 | 1297 |
Writing & Preference Yi-Lightning leads
Amazon Nova Micro: 39.5 (#247), Yi-Lightning: 50.2 (#184)
| Benchmark | Amazon Nova Micro | Yi-Lightning |
|---|---|---|
| LMArena Text | 1208 | 1302 |
| LMArena Creative Writing | 1172 | 1280 |
| LMArena Multi-Turn | 1178 | 1311 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.4 on the Noometry Index.
Is Amazon Nova Micro or Yi-Lightning better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 27.4 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Yi-Lightning share?
17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Yi-Lightning has 18.