Model comparison
Claude Opus 4 vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude Opus 4 scores higher in 3 categories and Inkling-Small in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 27.3.
- The biggest single-benchmark swing is ARC-AGI-1: 35.7% for Claude Opus 4 and 84% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Inkling-Small accepts more context: 524K tokens versus 200K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Inkling-Small | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 43.1 | 46.5 |
| Released | 2025-05-22 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 200K | 524K |
| Max output | 32K | 1.05M |
| Input $ / M tokens | $15 | $0.45 |
| Output $ / M tokens | $75 | $1.20 |
| Results tracked | 56 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Inkling-Small: 43.6 (#85)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Coding | 1442 | 1451 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Not comparable
Claude Opus 4: 34.8 (#42), Inkling-Small: —
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Inkling-Small leads
Claude Opus 4: 27.3 (#121), Inkling-Small: 38.6 (#63)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 8.6% | 40.1% |
| ARC-AGI-1 | 35.7% | 84% |
| CritPt | 0.3% | 8.3% |
| LMArena Hard Prompts | 1399 | 1423 |
| Epoch Capabilities Index | 142.67 | 150.15 |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| Chess Puzzles | — | 18% |
| EnigmaEval | 5.6% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| ForecastBench | 61.1 | — |
Math Inkling-Small leads
Claude Opus 4: 42.0 (#86), Inkling-Small: 45.1 (#77)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 90% |
| LMArena Math | 1390 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Inkling-Small leads
Claude Opus 4: 44.0 (#88), Inkling-Small: 48.2 (#77)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 76.3% | 88.5% |
| LMArena Expert | 1386 | 1442 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Inkling-Small leads
Claude Opus 4: 31.5 (#106), Inkling-Small: 39.1 (#62)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1192 | 1235 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Inkling-Small leads
Claude Opus 4: 48.8 (#138), Inkling-Small: 51.7 (#104)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1362 | 1402 |
| LMArena Chinese | 1386 | 1465 |
| LMArena French | 1372 | 1436 |
| LMArena German | 1391 | 1405 |
| LMArena Japanese | 1331 | 1405 |
| LMArena Korean | 1321 | 1363 |
| LMArena Russian | 1392 | 1391 |
| LMArena Spanish | 1389 | 1428 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Inkling-Small: 73.8 (#114)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1406 | 1399 |
| IFEval | 91.8% | — |
Long Context Inkling-Small leads
Claude Opus 4: 39.6 (#172), Inkling-Small: 42.7 (#118)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1422 | 1401 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Inkling-Small: 59.6 (#107)
| Benchmark | Claude Opus 4 | Inkling-Small |
|---|---|---|
| LMArena Text | 1377 | 1414 |
| LMArena Creative Writing | 1387 | 1331 |
| EQ-Bench Creative Writing | 1580 | 1491 |
| LMArena Multi-Turn | 1396 | 1418 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Inkling-Small better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 200K.
How many benchmarks do Claude Opus 4 and Inkling-Small share?
25 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Inkling-Small has 33.