Model comparison
Inkling-Small vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 46.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Kimi K2.5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Kimi K2.5 leads 52.1 to 42.7.
- The biggest single-benchmark swing is ARC-AGI-2: 40.1% for Inkling-Small and 11.8% for Kimi K2.5.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Kimi K2.5 | |
|---|---|---|
| Provider | Thinking Machines Lab | Moonshot AI |
| Noometry Index | 46.5 | 48.1 |
| Released | 2026-07-15 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $0.45 | $0.45 |
| Output $ / M tokens | $1.20 | $2.25 |
| Results tracked | 33 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Inkling-Small: 43.6 (#85), Kimi K2.5: 48.8 (#53)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1409 | 1437 |
| SciCode | 48.7% | 49% |
| LMArena Coding | 1451 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Kimi K2.5: 34.2 (#48)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Kimi K2.5: 31.2 (#80)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 40.1% | 11.8% |
| ARC-AGI-1 | 84% | 65.3% |
| CritPt | 8.3% | 3.1% |
| Chess Puzzles | 18% | 12% |
| LMArena Hard Prompts | 1423 | 1453 |
| Epoch Capabilities Index | 150.15 | 148.03 |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Mystery Game Puzzles | 6% | — |
Math Kimi K2.5 leads
Inkling-Small: 45.1 (#77), Kimi K2.5: 51.8 (#53)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 92.2% |
| LMArena Math | 1459 | 1470 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 62.3% |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Inkling-Small: 48.2 (#77), Kimi K2.5: 53.6 (#56)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 88.5% | 87.6% |
| SimpleQA Verified | 19.1% | 34.3% |
| LMArena Expert | 1442 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Kimi K2.5 leads
Inkling-Small: 39.1 (#62), Kimi K2.5: 41.1 (#39)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1235 | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Inkling-Small: 51.7 (#104), Kimi K2.5: 53.9 (#53)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1402 | 1433 |
| LMArena Chinese | 1465 | 1495 |
| LMArena French | 1436 | 1454 |
| LMArena German | 1405 | 1441 |
| LMArena Japanese | 1405 | 1421 |
| LMArena Korean | 1363 | 1410 |
| LMArena Russian | 1391 | 1435 |
| LMArena Spanish | 1428 | 1450 |
Instruction Following Kimi K2.5 leads
Inkling-Small: 73.8 (#114), Kimi K2.5: 75.3 (#64)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1431 |
Long Context Kimi K2.5 leads
Inkling-Small: 42.7 (#118), Kimi K2.5: 52.1 (#7)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1401 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Inkling-Small: 59.6 (#107), Kimi K2.5: 65.1 (#53)
| Benchmark | Inkling-Small | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1414 | 1445 |
| LMArena Creative Writing | 1331 | 1423 |
| EQ-Bench Creative Writing | 1491 | 1579 |
| LMArena Multi-Turn | 1418 | 1444 |
Frequently asked questions
Is Inkling-Small better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 46.5 on the Noometry Index.
Which is cheaper, Inkling-Small or Kimi K2.5?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Inkling-Small or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 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 K2.5 share?
29 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Kimi K2.5 has 51.