Model comparison
Claude Opus 5 vs Inkling
Claude Opus 5 is the stronger model overall, scoring 67.8 to 44.1 on the Noometry Index. Inkling costs 3.9× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and Inkling in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 31.3.
- The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 5 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- Claude Opus 5 accepts more context: 1M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5 | Inkling | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 67.8 | 44.1 |
| Released | 2026-07-24 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1M | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $5 | $1.87 |
| Output $ / M tokens | $25 | $4.68 |
| Results tracked | 57 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), Inkling: 34.5 (#234)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| FrontierCode | 53.4% | 14% |
| LMArena WebDev | 1691 | 1413 |
| FrontierSWE | 52% | 4.1% |
| SciCode | 56.4% | 47% |
| WeirdML | 91.8% | 32.3% |
| LMArena Coding | 1534 | 1464 |
| ALE-Bench | 2,165 | 946 |
| DeepSWE | 73.6% | — |
| CursorBench | 46.6% | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), Inkling: 29.6 (#85)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| APEX-Agents | 65.8% | 33.8% |
| τ²-bench Banking | 48.7% | 25% |
| OSWorld 2.0 | 31.4% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), Inkling: 40.4 (#56)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| ARC-AGI-2 | 90.4% | 36.5% |
| SimpleBench | 80.6% | 50% |
| ARC-AGI-1 | 97.5% | 79.5% |
| CritPt | 29.1% | 5.4% |
| Chess Puzzles | 42% | 21% |
| LMArena Hard Prompts | 1526 | 1451 |
| DTBench | 97.9% | 87.5% |
| LMCA | 64.5% | 37.6% |
| Epoch Capabilities Index | 162.78 | 148.54 |
| NYT Connections (extended) | 94.3% | — |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| Bench to the Future 3 | 0.12 | — |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), Inkling: 31.3 (#225)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 33.3% |
| FrontierMath Tier 4 | 73.2% | 4.9% |
| OTIS Mock AIME 2024-2025 | 98.9% | 88.9% |
| ProofBench | 99% | 0% |
| LMArena Math | 1531 | 1479 |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), Inkling: 55.1 (#49)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| GPQA Diamond | 93.9% | 88.3% |
| SimpleQA Verified | 59.9% | 40.3% |
| LMArena Expert | 1557 | 1465 |
Multimodal Not comparable
Claude Opus 5: 50.8 (#8), Inkling: —
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), Inkling: 54.0 (#52)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| LMArena Non-English | 1501 | 1434 |
| LMArena Chinese | 1574 | 1490 |
| LMArena French | 1519 | 1458 |
| LMArena German | 1524 | 1446 |
| LMArena Japanese | 1516 | 1429 |
| LMArena Korean | 1521 | 1404 |
| LMArena Russian | 1507 | 1429 |
| LMArena Spanish | 1519 | 1448 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), Inkling: 75.1 (#71)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1517 | 1426 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), Inkling: 43.8 (#86)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| LMArena Longer Query | 1515 | 1434 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), Inkling: 65.2 (#51)
| Benchmark | Claude Opus 5 | Inkling |
|---|---|---|
| LMArena Text | 1507 | 1441 |
| LMArena Creative Writing | 1491 | 1387 |
| EQ-Bench Creative Writing | 2133 | 1611 |
| EQ-Bench 4 | 1385 | 1226 |
| LMArena Multi-Turn | 1499 | 1436 |
Frequently asked questions
Is Claude Opus 5 better than Inkling?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 44.1 on the Noometry Index. Inkling costs 3.9× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Claude Opus 5 lists at $5 and $25.
Is Claude Opus 5 or Inkling better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 66K.
How many benchmarks do Claude Opus 5 and Inkling share?
41 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Inkling has 41.