Model comparison
Claude 3.7 Sonnet vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 39.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 84% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Inkling-Small | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 39.5 | 46.5 |
| Released | 2025-02-24 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | — | 524K |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 58 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Claude 3.7 Sonnet: 40.6 (#136), Inkling-Small: 43.6 (#85)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Coding | 1361 | 1451 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 34.1 (#50), Inkling-Small: —
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Inkling-Small leads
Claude 3.7 Sonnet: 18.6 (#277), Inkling-Small: 38.6 (#63)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 0.9% | 40.1% |
| ARC-AGI-1 | 28.6% | 84% |
| LMArena Hard Prompts | 1333 | 1423 |
| Epoch Capabilities Index | 141.16 | 150.15 |
| SimpleBench | 46.4% | — |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 6% |
| LiveBench Data Analysis | 74% | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Inkling-Small leads
Claude 3.7 Sonnet: 37.5 (#153), Inkling-Small: 45.1 (#77)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 90% |
| LMArena Math | 1337 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Inkling-Small leads
Claude 3.7 Sonnet: 39.8 (#130), Inkling-Small: 48.2 (#77)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| GPQA Diamond | 79.7% | 88.5% |
| LMArena Expert | 1321 | 1442 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Inkling-Small leads
Claude 3.7 Sonnet: 33.7 (#95), Inkling-Small: 39.1 (#62)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Vision | 1169 | 1235 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Inkling-Small leads
Claude 3.7 Sonnet: 44.1 (#179), Inkling-Small: 51.7 (#104)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1296 | 1402 |
| LMArena Chinese | 1299 | 1465 |
| LMArena French | 1303 | 1436 |
| LMArena German | 1301 | 1405 |
| LMArena Japanese | 1267 | 1405 |
| LMArena Korean | 1249 | 1363 |
| LMArena Russian | 1311 | 1391 |
| LMArena Spanish | 1298 | 1428 |
Instruction Following Too close to call
Claude 3.7 Sonnet: 72.9 (#125), Inkling-Small: 73.8 (#114)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1352 | 1399 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Inkling-Small: 42.7 (#118)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1373 | 1401 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Inkling-Small leads
Claude 3.7 Sonnet: 54.4 (#150), Inkling-Small: 59.6 (#107)
| Benchmark | Claude 3.7 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Text | 1314 | 1414 |
| LMArena Creative Writing | 1332 | 1331 |
| EQ-Bench Creative Writing | 1412 | 1491 |
| LMArena Multi-Turn | 1339 | 1418 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Inkling-Small share?
24 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Inkling-Small has 33.