Model comparison
Claude 3.5 Sonnet vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 34.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 44.9 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 90% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Inkling-Small | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 34.4 | 46.5 |
| Released | 2024-06-20 | 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 | 60 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Claude 3.5 Sonnet: 39.5 (#145), Inkling-Small: 43.3 (#80)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Coding | 1343 | 1451 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Inkling-Small: —
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Inkling-Small leads
Claude 3.5 Sonnet: 22.5 (#176), Inkling-Small: 39.0 (#53)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1424 |
| Epoch Capabilities Index | 133.55 | 150.13 |
| ARC-AGI-2 | — | 40.1% |
| SimpleBench | 41.4% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Inkling-Small leads
Claude 3.5 Sonnet: 18.0 (#282), Inkling-Small: 44.9 (#65)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 90% |
| LMArena Math | 1306 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Inkling-Small leads
Claude 3.5 Sonnet: 28.5 (#236), Inkling-Small: 48.3 (#71)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| GPQA Diamond | 55.3% | 88.5% |
| LMArena Expert | 1264 | 1442 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Inkling-Small leads
Claude 3.5 Sonnet: 26.0 (#115), Inkling-Small: 38.4 (#59)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Vision | 1125 | 1235 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Inkling-Small leads
Claude 3.5 Sonnet: 43.4 (#180), Inkling-Small: 51.7 (#102)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1283 | 1400 |
| LMArena Chinese | 1271 | 1458 |
| LMArena French | 1304 | 1438 |
| LMArena German | 1297 | 1412 |
| LMArena Japanese | 1234 | 1399 |
| LMArena Korean | 1200 | 1355 |
| LMArena Russian | 1305 | 1392 |
| LMArena Spanish | 1289 | 1426 |
Instruction Following Inkling-Small leads
Claude 3.5 Sonnet: 69.0 (#177), Inkling-Small: 73.9 (#112)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1297 | 1397 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Inkling-Small leads
Claude 3.5 Sonnet: 39.9 (#162), Inkling-Small: 42.7 (#113)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1311 | 1401 |
Writing & Preference Inkling-Small leads
Claude 3.5 Sonnet: 53.0 (#159), Inkling-Small: 59.8 (#102)
| Benchmark | Claude 3.5 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Text | 1298 | 1413 |
| LMArena Creative Writing | 1292 | 1330 |
| EQ-Bench Creative Writing | 1451 | 1491 |
| LMArena Multi-Turn | 1326 | 1420 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Inkling-Small share?
22 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Inkling-Small has 33.