Model comparison
Claude Opus 4.1 vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 41.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Opus 4.1 scores higher in 4 categories and Inkling in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 42.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 33.3% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Opus 4.1 accepts more context: 200K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 41.0 | 44.1 |
| Released | 2025-08-05 | 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 | 48 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), Inkling: 34.5 (#234)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| LMArena WebDev | 1390 | 1413 |
| WeirdML | 45.9% | 32.3% |
| LMArena Coding | 1479 | 1464 |
| ALE-Bench | 674.77 | 946 |
| SWE-bench Verified | 73.3% | — |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), Inkling: 29.6 (#85)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 33.8% |
| GDPval | 43.6% | — |
| τ²-bench Banking | — | 25% |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Inkling leads
Claude Opus 4.1: 32.2 (#76), Inkling: 40.4 (#56)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| SimpleBench | 60% | 50% |
| Chess Puzzles | 7% | 21% |
| LMArena Hard Prompts | 1443 | 1451 |
| DTBench | 80% | 87.5% |
| LMCA | 37.1% | 37.6% |
| Epoch Capabilities Index | 144.12 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| ForecastBench | 62 | — |
Math Inkling leads
Claude Opus 4.1: 22.3 (#277), Inkling: 31.3 (#225)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 33.3% |
| FrontierMath Tier 4 | 2.4% | 4.9% |
| OTIS Mock AIME 2024-2025 | 68.9% | 88.9% |
| LMArena Math | 1431 | 1479 |
| ProofBench | — | 0% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Inkling leads
Claude Opus 4.1: 42.0 (#101), Inkling: 55.1 (#49)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| GPQA Diamond | 77.3% | 88.3% |
| LMArena Expert | 1439 | 1465 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 40.3% |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), Inkling: —
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| VPCT | 35% | — |
Multilingual Inkling leads
Claude Opus 4.1: 52.0 (#95), Inkling: 54.0 (#52)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| LMArena Non-English | 1405 | 1434 |
| LMArena Chinese | 1427 | 1490 |
| LMArena French | 1431 | 1458 |
| LMArena German | 1413 | 1446 |
| LMArena Japanese | 1378 | 1429 |
| LMArena Korean | 1380 | 1404 |
| LMArena Russian | 1422 | 1429 |
| LMArena Spanish | 1448 | 1448 |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), Inkling: 75.1 (#71)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1435 | 1426 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), Inkling: 43.8 (#86)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| LMArena Longer Query | 1455 | 1434 |
Writing & Preference Inkling leads
Claude Opus 4.1: 62.4 (#74), Inkling: 65.2 (#51)
| Benchmark | Claude Opus 4.1 | Inkling |
|---|---|---|
| LMArena Text | 1419 | 1441 |
| LMArena Creative Writing | 1412 | 1387 |
| LMArena Multi-Turn | 1444 | 1436 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Claude Opus 4.1 better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Inkling better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.1 does, with 200K tokens against 66K.
How many benchmarks do Claude Opus 4.1 and Inkling share?
29 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Inkling has 41.