Model comparison
Qwen2.5 7B Instruct vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where Yi-Lightning leads 36.2 to 12.6.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 29.0 | 37.1 |
| Released | 2024-09 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 36.5 (#208), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1312 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.8 (#124), Yi-Lightning: —
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Yi-Lightning leads
Qwen2.5 7B Instruct: 14.8 (#322), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1302 |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.51 | — |
Math Yi-Lightning leads
Qwen2.5 7B Instruct: 12.6 (#306), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1300 |
Knowledge Yi-Lightning leads
Qwen2.5 7B Instruct: 17.0 (#286), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1286 |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Qwen2.5 7B Instruct: 63.2 (#231), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1278 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | — | 1297 |
Writing & Preference Yi-Lightning leads
Qwen2.5 7B Instruct: 48.8 (#195), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen2.5 7B Instruct | Yi-Lightning |
|---|---|---|
| LMArena Text | — | 1302 |
| LMArena Creative Writing | — | 1280 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1311 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.0 on the Noometry Index.
Is Qwen2.5 7B Instruct or Yi-Lightning better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen2.5 7B Instruct and Yi-Lightning share?
0 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Yi-Lightning has 18.