Model comparison
Amazon Nova Pro vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 31.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Kimi K2 (Jul 2025) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 43.9.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 65.4% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Amazon | Moonshot AI |
| Noometry Index | 31.0 | 41.2 |
| Released | 2024-12-03 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 300K | 262K |
| Max output | 10K | 262K |
| Input $ / M tokens | $0.80 | $0.57 |
| Output $ / M tokens | $3.20 | $2.30 |
| Results tracked | 38 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 35.1 (#229), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1270 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 16.7 (#147), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 59.1% |
| Terminal-Bench | — | 35.7% |
| TheAgentCompany | 1.7% | — |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 20.0 (#243), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1384 |
| Epoch Capabilities Index | 123.8 | 146.01 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| ForecastBench | — | 60.2 |
| LiveBench | 43.5% | — |
Math Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 28.5 (#243), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 24.2% | 65.4% |
| LMArena Math | 1252 | 1397 |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 27.4 (#250), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 67.3% | 81.9% |
| Confabulations | 30.1% | 20.4% |
| Vectara Hallucination Rate | 5.1% | 17.9% |
| GPQA (HELM) | 44.6% | 65.3% |
| LMArena Expert | 1211 | 1365 |
| Humanity's Last Exam | 4.4% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Kimi K2 (Jul 2025): —
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 39.7 (#223), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1234 | 1372 |
| LMArena Chinese | 1244 | 1415 |
| LMArena French | 1271 | 1379 |
| LMArena German | 1243 | 1387 |
| LMArena Japanese | 1200 | 1349 |
| LMArena Korean | 1203 | 1325 |
| LMArena Russian | 1240 | 1385 |
| LMArena Spanish | 1182 | 1386 |
Instruction Following Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 64.9 (#226), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 81.5% | 85% |
| LMArena Instruction Following | 1235 | 1348 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 38.1 (#205), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1255 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Amazon Nova Pro: 43.9 (#226), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Amazon Nova Pro | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1259 | 1380 |
| LMArena Creative Writing | 1212 | 1350 |
| Short-Story Creative Writing | 60.5% | 85.6% |
| WildBench | 77.7% | 86.2% |
| LMArena Multi-Turn | 1246 | 1371 |
| EQ-Bench Creative Writing | — | 1666 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 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 (Jul 2025) share?
27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Kimi K2 (Jul 2025) has 42.