Model comparison
Inkling vs Nova 2 Lite
Inkling is the stronger model overall, scoring 44.1 to 39.0 on the Noometry Index. Nova 2 Lite costs 3.0× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Inkling scores higher in 7 categories and Nova 2 Lite in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 26.4.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Nova 2 Lite accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Nova 2 Lite | |
|---|---|---|
| Provider | Thinking Machines Lab | Amazon |
| Noometry Index | 44.1 | 39.0 |
| Released | 2026-07-15 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 66K | 1M |
| Max output | 66K | 64K |
| Input $ / M tokens | $1.87 | $0.30 |
| Output $ / M tokens | $4.68 | $2.50 |
| Results tracked | 41 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Inkling: 34.1 (#229), Nova 2 Lite: 40.1 (#131)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1463 | 1386 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Inkling leads
Inkling: 29.5 (#76), Nova 2 Lite: 23.9 (#114)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Nova 2 Lite: 26.4 (#120)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1364 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.6 | — |
Math Nova 2 Lite leads
Inkling: 31.2 (#198), Nova 2 Lite: 34.8 (#154)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1482 | 1359 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.2 (#44), Nova 2 Lite: 42.5 (#88)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1468 | 1360 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multilingual Inkling leads
Inkling: 54.2 (#49), Nova 2 Lite: 47.3 (#148)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1434 | 1337 |
| LMArena Chinese | 1495 | 1364 |
| LMArena French | 1453 | 1381 |
| LMArena German | 1456 | 1343 |
| LMArena Japanese | 1428 | 1273 |
| LMArena Korean | 1401 | 1284 |
| LMArena Russian | 1430 | 1343 |
| LMArena Spanish | 1442 | 1372 |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Nova 2 Lite: 70.7 (#156)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1427 | 1335 |
Long Context Inkling leads
Inkling: 43.9 (#79), Nova 2 Lite: 40.6 (#145)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1436 | 1335 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Nova 2 Lite: 54.1 (#150)
| Benchmark | Inkling | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1443 | 1362 |
| LMArena Creative Writing | 1390 | 1291 |
| LMArena Multi-Turn | 1436 | 1338 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Nova 2 Lite?
Inkling is the stronger model overall, scoring 44.1 to 39.0 on the Noometry Index. Nova 2 Lite costs 3.0× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 66K.
How many benchmarks do Inkling and Nova 2 Lite share?
17 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Nova 2 Lite has 19.