Model comparison
Llama 3.2 3B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 36.5 to 28.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
MetaSummary
- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 1 category and Yi-Lightning in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.4 to 24.9.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 3B | Yi-Lightning | |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 28.4 | 36.5 |
| Released | 2024-09-24 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.2 3B: 27.1 (#314), Yi-Lightning: 27.0 (#315)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1098 | 1313 |
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Yi-Lightning: —
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Yi-Lightning leads
Llama 3.2 3B: 20.1 (#225), Yi-Lightning: 24.9 (#137)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1302 |
Math Yi-Lightning leads
Llama 3.2 3B: 29.9 (#213), Yi-Lightning: 33.5 (#173)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1126 | 1300 |
Knowledge Yi-Lightning leads
Llama 3.2 3B: 29.1 (#232), Yi-Lightning: 34.8 (#182)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1090 | 1286 |
Multilingual Yi-Lightning leads
Llama 3.2 3B: 26.4 (#276), Yi-Lightning: 42.4 (#191)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1019 | 1269 |
| LMArena Chinese | 1017 | 1320 |
| LMArena German | 1056 | 1267 |
| LMArena Russian | 949 | 1255 |
| LMArena French | — | 1304 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Llama 3.2 3B: 56.3 (#270), Yi-Lightning: 67.6 (#191)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1089 | 1278 |
Long Context Yi-Lightning leads
Llama 3.2 3B: 33.4 (#256), Yi-Lightning: 39.4 (#176)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1101 | 1297 |
Writing & Preference Yi-Lightning leads
Llama 3.2 3B: 24.9 (#302), Yi-Lightning: 50.4 (#178)
| Benchmark | Llama 3.2 3B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1110 | 1302 |
| LMArena Creative Writing | 1094 | 1280 |
| LMArena Multi-Turn | 1105 | 1311 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 36.5 to 28.4 on the Noometry Index.
Is Llama 3.2 3B or Yi-Lightning better for coding?
They score almost the same on coding (27.1 vs 27.0); test both on your own repository before choosing.
How many benchmarks do Llama 3.2 3B and Yi-Lightning share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Yi-Lightning has 18.