Model comparison
Qwen3.8 Max vs Yi-Lightning
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen3.8 Max scores higher in 8 categories and Yi-Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 36.2.
Side by side
| Qwen3.8 Max | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 56.8 | 37.1 |
| Released | 2026-08-02 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 39 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen3.8 Max: 53.5 (#29), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1502 | 1312 |
| DeepSWE | 57.5% | — |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1674 | — |
| FrontierSWE | 17.8% | — |
| SciCode | 53.2% | — |
Agentic & Tool Use Not comparable
Qwen3.8 Max: 45.4 (#14), Yi-Lightning: —
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| APEX-Agents | 63.3% | — |
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |
Reasoning Qwen3.8 Max leads
Qwen3.8 Max: 54.4 (#26), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1302 |
| NYT Connections (extended) | 88.3% | — |
| CritPt | 20% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| Epoch Capabilities Index | 156.41 | — |
Math Qwen3.8 Max leads
Qwen3.8 Max: 73.2 (#20), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Math | 1499 | 1300 |
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
Knowledge Qwen3.8 Max leads
Qwen3.8 Max: 61.7 (#27), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1507 | 1286 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
Multimodal Not comparable
Qwen3.8 Max: 37.2 (#75), Yi-Lightning: —
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |
Multilingual Qwen3.8 Max leads
Qwen3.8 Max: 56.7 (#18), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1472 | 1269 |
| LMArena Chinese | 1538 | 1320 |
| LMArena French | 1503 | 1305 |
| LMArena German | 1483 | 1267 |
| LMArena Japanese | 1467 | 1228 |
| LMArena Korean | 1461 | 1192 |
| LMArena Russian | 1481 | 1255 |
| LMArena Spanish | 1492 | 1315 |
Instruction Following Qwen3.8 Max leads
Qwen3.8 Max: 77.6 (#17), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1479 | 1278 |
Long Context Qwen3.8 Max leads
Qwen3.8 Max: 45.6 (#31), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1489 | 1297 |
Writing & Preference Qwen3.8 Max leads
Qwen3.8 Max: 67.1 (#30), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen3.8 Max | Yi-Lightning |
|---|---|---|
| LMArena Text | 1483 | 1302 |
| LMArena Creative Writing | 1479 | 1280 |
| LMArena Multi-Turn | 1489 | 1311 |
Frequently asked questions
Is Qwen3.8 Max better than Yi-Lightning?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.1 on the Noometry Index.
Is Qwen3.8 Max or Yi-Lightning better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen3.8 Max and Yi-Lightning share?
17 benchmarks have published results for both models. Qwen3.8 Max has 39 scored results on Noometry and Yi-Lightning has 18.