Model comparison
Inkling-Small vs Kimi K2 (Jul 2025)
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Inkling-Small scores higher in 7 categories and Kimi K2 (Jul 2025) in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 22.7.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Inkling-Small accepts more context: 524K tokens versus 262K.
Side by side
| Inkling-Small | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Thinking Machines Lab | Moonshot AI |
| Noometry Index | 46.5 | 40.9 |
| Released | 2026-07-15 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 524K | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $0.45 | $0.57 |
| Output $ / M tokens | $1.20 | $2.30 |
| Results tracked | 33 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Inkling-Small: 43.3 (#80), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Coding | 1451 | 1399 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
Inkling-Small: —, Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1384 |
| Epoch Capabilities Index | 150.13 | 146.02 |
| ARC-AGI-2 | 40.1% | — |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| ForecastBench | — | 60.2 |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1453 | 1396 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1442 | 1363 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), Kimi K2 (Jul 2025): —
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#102), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1400 | 1372 |
| LMArena Chinese | 1458 | 1416 |
| LMArena French | 1438 | 1379 |
| LMArena German | 1412 | 1386 |
| LMArena Japanese | 1399 | 1349 |
| LMArena Korean | 1355 | 1324 |
| LMArena Russian | 1392 | 1384 |
| LMArena Spanish | 1426 | 1383 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.9 (#112), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1397 | 1347 |
| IFEval | — | 85% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#113), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1401 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Inkling-Small: 59.8 (#102), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | Inkling-Small | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1413 | 1380 |
| LMArena Creative Writing | 1330 | 1349 |
| EQ-Bench Creative Writing | 1491 | 1666 |
| LMArena Multi-Turn | 1420 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
Frequently asked questions
Is Inkling-Small better than Kimi K2 (Jul 2025)?
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Which is cheaper, Inkling-Small or Kimi K2 (Jul 2025)?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Inkling-Small or Kimi K2 (Jul 2025) better for coding?
They score almost the same on coding (43.3 vs 43.1); test both on your own repository before choosing.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 262K.
How many benchmarks do Inkling-Small and Kimi K2 (Jul 2025) share?
19 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Kimi K2 (Jul 2025) has 42.