Model comparison
Inkling-Small vs Yi-Lightning
Inkling-Small is the stronger model overall, scoring 46.5 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Inkling-Small leads 43.6 to 27.4.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Yi-Lightning | |
|---|---|---|
| Provider | Thinking Machines Lab | 01.AI |
| Noometry Index | 46.5 | 37.1 |
| Released | 2026-07-15 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 524K | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Yi-Lightning: 27.4 (#320)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1451 | 1312 |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Yi-Lightning: 25.9 (#139)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1423 | 1302 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Yi-Lightning: 36.2 (#172)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Math | 1459 | 1300 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Yi-Lightning: 35.4 (#185)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1442 | 1286 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Yi-Lightning: —
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Yi-Lightning: 42.2 (#196)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1402 | 1269 |
| LMArena Chinese | 1465 | 1320 |
| LMArena French | 1436 | 1305 |
| LMArena German | 1405 | 1267 |
| LMArena Japanese | 1405 | 1228 |
| LMArena Korean | 1363 | 1192 |
| LMArena Russian | 1391 | 1255 |
| LMArena Spanish | 1428 | 1315 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Yi-Lightning: 67.4 (#196)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1399 | 1278 |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), Yi-Lightning: 39.4 (#181)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1401 | 1297 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Yi-Lightning: 50.2 (#184)
| Benchmark | Inkling-Small | Yi-Lightning |
|---|---|---|
| LMArena Text | 1414 | 1302 |
| LMArena Creative Writing | 1331 | 1280 |
| LMArena Multi-Turn | 1418 | 1311 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Yi-Lightning?
Inkling-Small is the stronger model overall, scoring 46.5 to 37.1 on the Noometry Index.
Is Inkling-Small or Yi-Lightning better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 27.4 in the Noometry coding category.
How many benchmarks do Inkling-Small and Yi-Lightning share?
17 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Yi-Lightning has 18.