Model comparison
Amazon Nova Micro vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 98× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Kimi K3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 26.9.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 128K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Kimi K3 | |
|---|---|---|
| Provider | Amazon | Moonshot AI |
| Noometry Index | 30.4 | 59.5 |
| Released | 2024-12-03 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 128K | 1.05M |
| Max output | 10K | 1.05M |
| Input $ / M tokens | $0.035 | $3 |
| Output $ / M tokens | $0.14 | $15 |
| Results tracked | 32 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Amazon Nova Micro: 30.5 (#295), Kimi K3: 61.0 (#10)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Coding | 1218 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 1,524 |
Agentic & Tool Use Kimi K3 leads
Amazon Nova Micro: 22.1 (#132), Kimi K3: 41.8 (#20)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Amazon Nova Micro: 17.4 (#294), Kimi K3: 63.0 (#17)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
| LiveBench | 29.6% | — |
Math Kimi K3 leads
Amazon Nova Micro: 26.9 (#254), Kimi K3: 74.2 (#16)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Math | 1206 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Kimi K3 leads
Amazon Nova Micro: 29.6 (#237), Kimi K3: 63.2 (#21)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Expert | 1184 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Kimi K3: 37.8 (#70)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Amazon Nova Micro: 36.5 (#239), Kimi K3: 56.3 (#21)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1186 | 1466 |
| LMArena Chinese | 1209 | 1529 |
| LMArena French | 1238 | 1491 |
| LMArena German | 1192 | 1488 |
| LMArena Japanese | 1154 | 1487 |
| LMArena Korean | 1150 | 1458 |
| LMArena Russian | 1185 | 1482 |
| LMArena Spanish | 1225 | 1472 |
Instruction Following Kimi K3 leads
Amazon Nova Micro: 56.3 (#272), Kimi K3: 77.7 (#14)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1483 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Kimi K3 leads
Amazon Nova Micro: 36.5 (#229), Kimi K3: 45.8 (#29)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1205 | 1494 |
Writing & Preference Kimi K3 leads
Amazon Nova Micro: 39.5 (#247), Kimi K3: 76.6 (#4)
| Benchmark | Amazon Nova Micro | Kimi K3 |
|---|---|---|
| LMArena Text | 1208 | 1476 |
| LMArena Creative Writing | 1172 | 1454 |
| LMArena Multi-Turn | 1178 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| WildBench | 74.3% | — |
| EQ-Bench 4 | — | 1339 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 98× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Kimi K3?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Kimi K3 lists at $3 and $15.
Is Amazon Nova Micro or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 128K.
How many benchmarks do Amazon Nova Micro and Kimi K3 share?
17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Kimi K3 has 53.