Model comparison
Qwen3.5 27B vs Yi-Lightning
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 36.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen3.5 27B 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 Qwen3.5 27B leads 38.6 to 27.0.
- Qwen3.5 27B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5 27B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 41.4 | 36.5 |
| Released | 2026-02-23 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.40 | — |
| Results tracked | 28 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 27B leads
Qwen3.5 27B: 38.6 (#159), Yi-Lightning: 27.0 (#315)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1427 | 1313 |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1357 | — |
| WeirdML | 39.5% | — |
| ALE-Bench | 349.45 | — |
Agentic & Tool Use Not comparable
Qwen3.5 27B: —, Yi-Lightning: —
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| Vending-Bench 2 | 201.98 | — |
Reasoning Qwen3.5 27B leads
Qwen3.5 27B: 26.6 (#116), Yi-Lightning: 24.9 (#137)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1414 | 1302 |
| NYT Connections (extended) | 47.9% | — |
| Thematic Generalization | 45.5% | — |
| DTBench | 82.4% | — |
| LMCA | 34% | — |
Math Qwen3.5 27B leads
Qwen3.5 27B: 36.8 (#103), Yi-Lightning: 33.5 (#173)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1428 | 1300 |
| MathArena Final-Answer Competitions | 56.7% | — |
Knowledge Qwen3.5 27B leads
Qwen3.5 27B: 37.4 (#149), Yi-Lightning: 34.8 (#182)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1428 | 1286 |
| Vectara Hallucination Rate | 12.1% | — |
Multimodal Not comparable
Qwen3.5 27B: 38.7 (#56), Yi-Lightning: —
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Qwen3.5 27B leads
Qwen3.5 27B: 51.0 (#112), Yi-Lightning: 42.4 (#191)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1390 | 1269 |
| LMArena Chinese | 1478 | 1320 |
| LMArena French | 1409 | 1304 |
| LMArena German | 1393 | 1267 |
| LMArena Japanese | 1345 | 1228 |
| LMArena Korean | 1359 | 1192 |
| LMArena Russian | 1389 | 1255 |
| LMArena Spanish | 1408 | 1315 |
Instruction Following Qwen3.5 27B leads
Qwen3.5 27B: 73.7 (#114), Yi-Lightning: 67.6 (#191)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1393 | 1278 |
Long Context Qwen3.5 27B leads
Qwen3.5 27B: 43.1 (#103), Yi-Lightning: 39.4 (#176)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1413 | 1297 |
Writing & Preference Qwen3.5 27B leads
Qwen3.5 27B: 59.5 (#106), Yi-Lightning: 50.4 (#178)
| Benchmark | Qwen3.5 27B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1409 | 1302 |
| LMArena Creative Writing | 1362 | 1280 |
| LMArena Multi-Turn | 1410 | 1311 |
Frequently asked questions
Is Qwen3.5 27B better than Yi-Lightning?
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 36.5 on the Noometry Index.
Is Qwen3.5 27B or Yi-Lightning better for coding?
Qwen3.5 27B scores higher on coding benchmarks: 38.6 versus 27.0 in the Noometry coding category.
How many benchmarks do Qwen3.5 27B and Yi-Lightning share?
17 benchmarks have published results for both models. Qwen3.5 27B has 28 scored results on Noometry and Yi-Lightning has 18.