Model comparison
Qwen3 235B-A22B vs Yi-Lightning
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 7 categories and Yi-Lightning in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3 235B-A22B leads 44.3 to 27.4.
- The biggest single-benchmark swing is Aider Polyglot: 59.6% for Qwen3 235B-A22B and 12.9% for Yi-Lightning.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 235B-A22B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 43.5 | 37.1 |
| Released | 2025-04 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 49 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 44.3 (#75), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 59.6% | 12.9% |
| LMArena Coding | 1445 | 1312 |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Yi-Lightning: —
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |
Reasoning Yi-Lightning leads
Qwen3 235B-A22B: 15.7 (#311), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1302 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 29.3% | — |
| Epoch Capabilities Index | 143.85 | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1432 | 1300 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3 235B-A22B leads
Qwen3 235B-A22B: 49.6 (#73), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1463 | 1286 |
| GPQA Diamond | 80.1% | — |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
Multilingual Qwen3 235B-A22B leads
Qwen3 235B-A22B: 52.3 (#89), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1409 | 1269 |
| LMArena Chinese | 1481 | 1320 |
| LMArena French | 1445 | 1305 |
| LMArena German | 1433 | 1267 |
| LMArena Japanese | 1399 | 1228 |
| LMArena Korean | 1391 | 1192 |
| LMArena Russian | 1411 | 1255 |
| LMArena Spanish | 1430 | 1315 |
Instruction Following Qwen3 235B-A22B leads
Qwen3 235B-A22B: 72.6 (#136), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1408 | 1278 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1426 | 1297 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.6 (#108), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen3 235B-A22B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1419 | 1302 |
| LMArena Creative Writing | 1384 | 1280 |
| LMArena Multi-Turn | 1432 | 1311 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Yi-Lightning?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.1 on the Noometry Index.
Is Qwen3 235B-A22B or Yi-Lightning better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen3 235B-A22B and Yi-Lightning share?
18 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Yi-Lightning has 18.