Model comparison
Claude Sonnet 4.5 vs Inkling
Claude Sonnet 4.5 and Inkling score almost the same on the Noometry Index (44.1 vs 44.1), so choose on price, context window or the category you care about most.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 5 categories and Inkling in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 26.9.
- The biggest single-benchmark swing is ARC-AGI-2: 13.6% for Claude Sonnet 4.5 and 36.5% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Claude Sonnet 4.5 accepts more context: 200K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 44.1 | 44.1 |
| Released | 2025-09-29 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 200K | 66K |
| Max output | 64K | 66K |
| Input $ / M tokens | $3 | $1.87 |
| Output $ / M tokens | $15 | $4.68 |
| Results tracked | 73 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 47.3 (#61), Inkling: 34.5 (#234)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| LMArena WebDev | 1393 | 1413 |
| SciCode | 44.7% | 47% |
| WeirdML | 47.7% | 32.3% |
| LMArena Coding | 1489 | 1464 |
| ALE-Bench | 796.15 | 946 |
| SWE-bench Verified | 71.3% | — |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| FrontierSWE | — | 4.1% |
| GSO | 14.7% | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.3 (#32), Inkling: 29.6 (#85)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| τ²-bench Banking | 25.3% | 25% |
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Inkling leads
Claude Sonnet 4.5: 26.9 (#125), Inkling: 40.4 (#56)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| ARC-AGI-2 | 13.6% | 36.5% |
| SimpleBench | 54.3% | 50% |
| ARC-AGI-1 | 63.7% | 79.5% |
| CritPt | 1.1% | 5.4% |
| Chess Puzzles | 12% | 21% |
| LMArena Hard Prompts | 1462 | 1451 |
| DTBench | 83.2% | 87.5% |
| LMCA | 38.8% | 37.6% |
| Epoch Capabilities Index | 146.84 | 148.54 |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| ForecastBench | 61.9 | — |
Math Too close to call
Claude Sonnet 4.5: 32.3 (#216), Inkling: 31.3 (#225)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 33.3% |
| FrontierMath Tier 4 | 2.4% | 4.9% |
| OTIS Mock AIME 2024-2025 | 77.8% | 88.9% |
| ProofBench | 19% | 0% |
| LMArena Math | 1449 | 1479 |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Inkling leads
Claude Sonnet 4.5: 48.4 (#76), Inkling: 55.1 (#49)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| GPQA Diamond | 82.3% | 88.3% |
| SimpleQA Verified | 30.7% | 40.3% |
| LMArena Expert | 1482 | 1465 |
| Humanity's Last Exam | 13.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Inkling: —
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Too close to call
Claude Sonnet 4.5: 53.4 (#69), Inkling: 54.0 (#52)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| LMArena Non-English | 1425 | 1434 |
| LMArena Chinese | 1459 | 1490 |
| LMArena French | 1458 | 1458 |
| LMArena German | 1427 | 1446 |
| LMArena Japanese | 1390 | 1429 |
| LMArena Korean | 1403 | 1404 |
| LMArena Russian | 1437 | 1429 |
| LMArena Spanish | 1457 | 1448 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Inkling: 75.1 (#71)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1459 | 1426 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Inkling: 43.8 (#86)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1476 | 1434 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Inkling: 65.2 (#51)
| Benchmark | Claude Sonnet 4.5 | Inkling |
|---|---|---|
| LMArena Text | 1439 | 1441 |
| LMArena Creative Writing | 1442 | 1387 |
| EQ-Bench Creative Writing | 1678 | 1611 |
| LMArena Multi-Turn | 1465 | 1436 |
| WildBench | 85.4% | — |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Claude Sonnet 4.5 better than Inkling?
Claude Sonnet 4.5 and Inkling score almost the same on the Noometry Index (44.1 vs 44.1), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4.5 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Inkling better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.5 does, with 200K tokens against 66K.
How many benchmarks do Claude Sonnet 4.5 and Inkling share?
37 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Inkling has 41.