Model comparison
Amazon Nova Micro vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 15× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Kimi K2.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 leads 65.1 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 14.2% for Kimi K2.5.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 128K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Kimi K2.5 | |
|---|---|---|
| Provider | Amazon | Moonshot AI |
| Noometry Index | 30.4 | 48.1 |
| Released | 2024-12-03 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 10K | 262K |
| Input $ / M tokens | $0.035 | $0.45 |
| Output $ / M tokens | $0.14 | $2.25 |
| Results tracked | 32 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Amazon Nova Micro: 30.5 (#295), Kimi K2.5: 48.8 (#53)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1218 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Kimi K2.5 leads
Amazon Nova Micro: 22.1 (#132), Kimi K2.5: 34.2 (#48)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Amazon Nova Micro: 17.4 (#294), Kimi K2.5: 31.2 (#80)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1453 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| Epoch Capabilities Index | — | 148.03 |
| LiveBench | 29.6% | — |
Math Kimi K2.5 leads
Amazon Nova Micro: 26.9 (#254), Kimi K2.5: 51.8 (#53)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1206 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Amazon Nova Micro: 29.6 (#237), Kimi K2.5: 53.6 (#56)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 14.2% |
| LMArena Expert | 1184 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Kimi K2.5: 41.1 (#39)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Amazon Nova Micro: 36.5 (#239), Kimi K2.5: 53.9 (#53)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1186 | 1433 |
| LMArena Chinese | 1209 | 1495 |
| LMArena French | 1238 | 1454 |
| LMArena German | 1192 | 1441 |
| LMArena Japanese | 1154 | 1421 |
| LMArena Korean | 1150 | 1410 |
| LMArena Russian | 1185 | 1435 |
| LMArena Spanish | 1225 | 1450 |
Instruction Following Kimi K2.5 leads
Amazon Nova Micro: 56.3 (#272), Kimi K2.5: 75.3 (#64)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1431 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Kimi K2.5 leads
Amazon Nova Micro: 36.5 (#229), Kimi K2.5: 52.1 (#7)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1205 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Amazon Nova Micro: 39.5 (#247), Kimi K2.5: 65.1 (#53)
| Benchmark | Amazon Nova Micro | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1208 | 1445 |
| LMArena Creative Writing | 1172 | 1423 |
| LMArena Multi-Turn | 1178 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 15× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Kimi K2.5?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Amazon Nova Micro or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Kimi K2.5 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Kimi K2.5 has 51.