Model comparison
Claude Opus 4 vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 43.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Claude Opus 4 scores higher in 4 categories and Inkling in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 27.3.
- The biggest single-benchmark swing is ARC-AGI-1: 35.7% for Claude Opus 4 and 79.5% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Opus 4 accepts more context: 200K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 43.1 | 44.1 |
| Released | 2025-05-22 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 200K | 66K |
| Max output | 32K | 66K |
| Input $ / M tokens | $15 | $1.87 |
| Output $ / M tokens | $75 | $4.68 |
| Results tracked | 56 | 41 |
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: 34.5 (#234)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| WeirdML | 43.7% | 32.3% |
| LMArena Coding | 1442 | 1464 |
| SWE-bench Verified | 70.7% | — |
| FrontierCode | — | 14% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| GSO | 6.9% | — |
| ALE-Bench | — | 946 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Inkling: 29.6 (#85)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Inkling leads
Claude Opus 4: 27.3 (#121), Inkling: 40.4 (#56)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| ARC-AGI-2 | 8.6% | 36.5% |
| SimpleBench | 58.8% | 50% |
| ARC-AGI-1 | 35.7% | 79.5% |
| CritPt | 0.3% | 5.4% |
| LMArena Hard Prompts | 1399 | 1451 |
| DTBench | 81.6% | 87.5% |
| LMCA | 37.4% | 37.6% |
| Epoch Capabilities Index | 142.67 | 148.54 |
| Kagi LLM Benchmark | 74.3% | — |
| Chess Puzzles | — | 21% |
| EnigmaEval | 5.6% | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Inkling: 31.3 (#225)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 88.9% |
| LMArena Math | 1390 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Inkling leads
Claude Opus 4: 44.0 (#88), Inkling: 55.1 (#49)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| GPQA Diamond | 76.3% | 88.3% |
| LMArena Expert | 1386 | 1465 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 40.3% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), Inkling: —
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Inkling leads
Claude Opus 4: 48.8 (#138), Inkling: 54.0 (#52)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| LMArena Non-English | 1362 | 1434 |
| LMArena Chinese | 1386 | 1490 |
| LMArena French | 1372 | 1458 |
| LMArena German | 1391 | 1446 |
| LMArena Japanese | 1331 | 1429 |
| LMArena Korean | 1321 | 1404 |
| LMArena Russian | 1392 | 1429 |
| LMArena Spanish | 1389 | 1448 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Inkling: 75.1 (#71)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1406 | 1426 |
| IFEval | 91.8% | — |
Long Context Inkling leads
Claude Opus 4: 39.6 (#172), Inkling: 43.8 (#86)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| LMArena Longer Query | 1422 | 1434 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Inkling leads
Claude Opus 4: 61.2 (#89), Inkling: 65.2 (#51)
| Benchmark | Claude Opus 4 | Inkling |
|---|---|---|
| LMArena Text | 1377 | 1441 |
| LMArena Creative Writing | 1387 | 1387 |
| EQ-Bench Creative Writing | 1580 | 1611 |
| LMArena Multi-Turn | 1396 | 1436 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Claude Opus 4 better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Inkling better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 66K.
How many benchmarks do Claude Opus 4 and Inkling share?
28 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Inkling has 41.