Model comparison
Amazon Nova Pro vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 31.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Kimi K2.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 28.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 10.8% for Kimi K2.6.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Kimi K2.6 | |
|---|---|---|
| Provider | Amazon | Moonshot AI |
| Noometry Index | 31.0 | 47.7 |
| Released | 2024-12-03 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 262K |
| Input $ / M tokens | $0.80 | $0.95 |
| Output $ / M tokens | $3.20 | $4 |
| Results tracked | 38 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Amazon Nova Pro: 35.1 (#229), Kimi K2.6: 50.7 (#43)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Coding | 1270 | 1488 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Kimi K2.6 leads
Amazon Nova Pro: 16.7 (#147), Kimi K2.6: 21.9 (#137)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| OSWorld 2.0 | — | 4.6% |
| TheAgentCompany | 1.7% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Amazon Nova Pro: 20.0 (#243), Kimi K2.6: 40.5 (#55)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1470 |
| Epoch Capabilities Index | 123.8 | 151.05 |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 37.3% |
| LiveBench | 43.5% | — |
Math Kimi K2.6 leads
Amazon Nova Pro: 28.5 (#243), Kimi K2.6: 57.0 (#41)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1252 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Amazon Nova Pro: 27.4 (#250), Kimi K2.6: 54.0 (#54)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 10.8% |
| LMArena Expert | 1211 | 1491 |
| GPQA Diamond | — | 90.8% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Kimi K2.6 leads
Amazon Nova Pro: 25.0 (#126), Kimi K2.6: 31.6 (#103)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 980 | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Amazon Nova Pro: 39.7 (#223), Kimi K2.6: 54.9 (#37)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1234 | 1446 |
| LMArena Chinese | 1244 | 1521 |
| LMArena French | 1271 | 1471 |
| LMArena German | 1243 | 1450 |
| LMArena Japanese | 1200 | 1443 |
| LMArena Korean | 1203 | 1427 |
| LMArena Russian | 1240 | 1446 |
| LMArena Spanish | 1182 | 1464 |
Instruction Following Kimi K2.6 leads
Amazon Nova Pro: 64.9 (#226), Kimi K2.6: 76.3 (#43)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1451 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Kimi K2.6 leads
Amazon Nova Pro: 38.1 (#205), Kimi K2.6: 44.9 (#52)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1255 | 1468 |
Writing & Preference Kimi K2.6 leads
Amazon Nova Pro: 43.9 (#226), Kimi K2.6: 68.5 (#26)
| Benchmark | Amazon Nova Pro | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1259 | 1455 |
| LMArena Creative Writing | 1212 | 1434 |
| LMArena Multi-Turn | 1246 | 1453 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1725 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1202 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Kimi K2.6?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Amazon Nova Pro or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 262K.
How many benchmarks do Amazon Nova Pro and Kimi K2.6 share?
20 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Kimi K2.6 has 51.