Model comparison
Claude Sonnet 5 vs Inkling
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 44.1 on the Noometry Index. Inkling costs 1.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Inkling in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 31.3.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 54.6 | 44.1 |
| Released | 2026-06-29 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1M | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1.87 |
| Output $ / M tokens | $10 | $4.68 |
| Results tracked | 51 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), Inkling: 34.5 (#234)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| FrontierCode | 42.7% | 14% |
| LMArena WebDev | 1541 | 1413 |
| SciCode | 54.3% | 47% |
| WeirdML | 68.8% | 32.3% |
| LMArena Coding | 1483 | 1464 |
| ALE-Bench | 1,463 | 946 |
| DeepSWE | 53.8% | — |
| CursorBench | 34.1% | — |
| FrontierSWE | — | 4.1% |
| GSO | 37.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), Inkling: 29.6 (#85)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| APEX-Agents | 54.5% | 33.8% |
| τ²-bench Banking | — | 25% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), Inkling: 40.4 (#56)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| SimpleBench | 60.6% | 50% |
| CritPt | 16.9% | 5.4% |
| Chess Puzzles | 35% | 21% |
| LMArena Hard Prompts | 1461 | 1451 |
| DTBench | 92.5% | 87.5% |
| LMCA | 50% | 37.6% |
| Epoch Capabilities Index | 156.21 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 79.5% |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), Inkling: 31.3 (#225)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 33.3% |
| FrontierMath Tier 4 | 29.3% | 4.9% |
| OTIS Mock AIME 2024-2025 | 94.7% | 88.9% |
| ProofBench | 77% | 0% |
| LMArena Math | 1467 | 1479 |
Knowledge Too close to call
Claude Sonnet 5: 55.6 (#47), Inkling: 55.1 (#49)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| GPQA Diamond | 90.5% | 88.3% |
| SimpleQA Verified | 33.7% | 40.3% |
| LMArena Expert | 1490 | 1465 |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), Inkling: —
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Too close to call
Claude Sonnet 5: 53.8 (#55), Inkling: 54.0 (#52)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| LMArena Non-English | 1431 | 1434 |
| LMArena Chinese | 1477 | 1490 |
| LMArena French | 1460 | 1458 |
| LMArena German | 1440 | 1446 |
| LMArena Japanese | 1422 | 1429 |
| LMArena Korean | 1411 | 1404 |
| LMArena Russian | 1451 | 1429 |
| LMArena Spanish | 1437 | 1448 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), Inkling: 75.1 (#71)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1452 | 1426 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), Inkling: 43.8 (#86)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1463 | 1434 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), Inkling: 65.2 (#51)
| Benchmark | Claude Sonnet 5 | Inkling |
|---|---|---|
| LMArena Text | 1442 | 1441 |
| LMArena Creative Writing | 1416 | 1387 |
| EQ-Bench Creative Writing | 1794 | 1611 |
| EQ-Bench 4 | 1236 | 1226 |
| LMArena Multi-Turn | 1454 | 1436 |
Frequently asked questions
Is Claude Sonnet 5 better than Inkling?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 44.1 on the Noometry Index. Inkling costs 1.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Inkling better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 66K.
How many benchmarks do Claude Sonnet 5 and Inkling share?
37 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Inkling has 41.