Model comparison
Amazon Nova Pro vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 31.0 on the Noometry Index. Amazon Nova Pro costs 1.8× less per token, which makes it the better buy when Inkling'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 Pro scores higher in 1 category and Inkling in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 27.4.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Amazon Nova Pro accepts more context: 300K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Inkling | |
|---|---|---|
| Provider | Amazon | Thinking Machines Lab |
| Noometry Index | 31.0 | 44.1 |
| Released | 2024-12-03 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 300K | 66K |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.80 | $1.87 |
| Output $ / M tokens | $3.20 | $4.68 |
| Results tracked | 38 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Pro: 35.1 (#229), Inkling: 34.5 (#234)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Coding | 1270 | 1464 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 946 |
Agentic & Tool Use Inkling leads
Amazon Nova Pro: 16.7 (#147), Inkling: 29.6 (#85)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
Amazon Nova Pro: 20.0 (#243), Inkling: 40.4 (#56)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1451 |
| Epoch Capabilities Index | 123.8 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 87.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 37.6% |
| LiveBench | 43.5% | — |
Math Inkling leads
Amazon Nova Pro: 28.5 (#243), Inkling: 31.3 (#225)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Math | 1252 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Inkling leads
Amazon Nova Pro: 27.4 (#250), Inkling: 55.1 (#49)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Expert | 1211 | 1465 |
| GPQA Diamond | — | 88.3% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 40.3% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Inkling: —
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Inkling leads
Amazon Nova Pro: 39.7 (#223), Inkling: 54.0 (#52)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Non-English | 1234 | 1434 |
| LMArena Chinese | 1244 | 1490 |
| LMArena French | 1271 | 1458 |
| LMArena German | 1243 | 1446 |
| LMArena Japanese | 1200 | 1429 |
| LMArena Korean | 1203 | 1404 |
| LMArena Russian | 1240 | 1429 |
| LMArena Spanish | 1182 | 1448 |
Instruction Following Inkling leads
Amazon Nova Pro: 64.9 (#226), Inkling: 75.1 (#71)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Instruction Following | 1235 | 1426 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Inkling leads
Amazon Nova Pro: 38.1 (#205), Inkling: 43.8 (#86)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Longer Query | 1255 | 1434 |
Writing & Preference Inkling leads
Amazon Nova Pro: 43.9 (#226), Inkling: 65.2 (#51)
| Benchmark | Amazon Nova Pro | Inkling |
|---|---|---|
| LMArena Text | 1259 | 1441 |
| LMArena Creative Writing | 1212 | 1387 |
| LMArena Multi-Turn | 1246 | 1436 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1611 |
| WildBench | 77.7% | — |
| EQ-Bench 4 | — | 1226 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 31.0 on the Noometry Index. Amazon Nova Pro costs 1.8× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Inkling?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Amazon Nova Pro or Inkling better for coding?
They score almost the same on coding (35.1 vs 34.5); test both on your own repository before choosing.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 66K.
How many benchmarks do Amazon Nova Pro and Inkling share?
18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Inkling has 41.