Model comparison
Inkling-Small vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 46.5 on the Noometry Index. Inkling-Small costs 2.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Kimi K2.6 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 45.1.
- The biggest single-benchmark swing is SimpleQA Verified: 19.1% for Inkling-Small and 34.9% for Kimi K2.6.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Kimi K2.6 | |
|---|---|---|
| Provider | Thinking Machines Lab | Moonshot AI |
| Noometry Index | 46.5 | 47.7 |
| Released | 2026-07-15 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $0.45 | $0.95 |
| Output $ / M tokens | $1.20 | $4 |
| Results tracked | 33 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Inkling-Small: 43.6 (#85), Kimi K2.6: 50.7 (#43)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1409 | 1509 |
| SciCode | 48.7% | 53.5% |
| LMArena Coding | 1451 | 1488 |
| SWE-bench Verified | — | 76.7% |
| WeirdML | — | 55.9% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Kimi K2.6: 21.9 (#137)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Inkling-Small: 38.6 (#63), Kimi K2.6: 40.5 (#55)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| CritPt | 8.3% | 8% |
| Chess Puzzles | 18% | 26% |
| LMArena Hard Prompts | 1423 | 1470 |
| Mystery Game Puzzles | 6% | 18% |
| Epoch Capabilities Index | 150.15 | 151.05 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 84% | — |
| EBR-Bench | — | 2.4% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
Math Kimi K2.6 leads
Inkling-Small: 45.1 (#77), Kimi K2.6: 57.0 (#41)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 57.2% |
| FrontierMath Tier 4 | 17.1% | 25.6% |
| OTIS Mock AIME 2024-2025 | 90% | 96.1% |
| ProofBench | 6% | 16% |
| LMArena Math | 1459 | 1475 |
| MathArena Final-Answer Competitions | — | 72.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Inkling-Small: 48.2 (#77), Kimi K2.6: 54.0 (#54)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 88.5% | 90.8% |
| SimpleQA Verified | 19.1% | 34.9% |
| LMArena Expert | 1442 | 1491 |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Inkling-Small leads
Inkling-Small: 39.1 (#62), Kimi K2.6: 31.6 (#103)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1235 | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Inkling-Small: 51.7 (#104), Kimi K2.6: 54.9 (#37)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1402 | 1446 |
| LMArena Chinese | 1465 | 1521 |
| LMArena French | 1436 | 1471 |
| LMArena German | 1405 | 1450 |
| LMArena Japanese | 1405 | 1443 |
| LMArena Korean | 1363 | 1427 |
| LMArena Russian | 1391 | 1446 |
| LMArena Spanish | 1428 | 1464 |
Instruction Following Kimi K2.6 leads
Inkling-Small: 73.8 (#114), Kimi K2.6: 76.3 (#43)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1451 |
Long Context Kimi K2.6 leads
Inkling-Small: 42.7 (#118), Kimi K2.6: 44.9 (#52)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1401 | 1468 |
Writing & Preference Kimi K2.6 leads
Inkling-Small: 59.6 (#107), Kimi K2.6: 68.5 (#26)
| Benchmark | Inkling-Small | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1414 | 1455 |
| LMArena Creative Writing | 1331 | 1434 |
| EQ-Bench Creative Writing | 1491 | 1725 |
| LMArena Multi-Turn | 1418 | 1453 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Inkling-Small better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 46.5 on the Noometry Index. Inkling-Small costs 2.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Kimi K2.6?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Inkling-Small or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Inkling-Small and Kimi K2.6 share?
31 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Kimi K2.6 has 51.