Model comparison
Gemma 3 4B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 2 categories and Yi-Lightning in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 11.8.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Yi-Lightning | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 28.1 | 37.1 |
| Released | 2025-03-12 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), Yi-Lightning: 27.4 (#320)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1230 | 1312 |
| Aider Polyglot | — | 12.9% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Yi-Lightning: —
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Yi-Lightning leads
Gemma 3 4B: 13.2 (#335), Yi-Lightning: 25.9 (#139)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1302 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Yi-Lightning leads
Gemma 3 4B: 16.8 (#292), Yi-Lightning: 36.2 (#172)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1239 | 1300 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Yi-Lightning leads
Gemma 3 4B: 11.8 (#299), Yi-Lightning: 35.4 (#185)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1223 | 1286 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Too close to call
Gemma 3 4B: 42.5 (#194), Yi-Lightning: 42.2 (#196)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1273 | 1269 |
| LMArena German | 1281 | 1267 |
| LMArena Russian | 1294 | 1255 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Gemma 3 4B: 65.2 (#225), Yi-Lightning: 67.4 (#196)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1239 | 1278 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Yi-Lightning: 39.4 (#181)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1273 | 1297 |
Writing & Preference Yi-Lightning leads
Gemma 3 4B: 42.0 (#239), Yi-Lightning: 50.2 (#184)
| Benchmark | Gemma 3 4B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1291 | 1302 |
| LMArena Creative Writing | 1271 | 1280 |
| LMArena Multi-Turn | 1255 | 1311 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Yi-Lightning better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 27.4 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Yi-Lightning share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Yi-Lightning has 18.