Model comparison
Gemma 3 4B vs Yi-34B
Gemma 3 4B and Yi-34B score almost the same on the Noometry Index (28.1 vs 27.8), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
GoogleSummary
- They share 14 benchmarks with published results for both. Gemma 3 4B scores higher in 6 categories and Yi-34B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 4B leads 42.5 to 29.7.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 14.7% for Yi-34B.
Side by side
| Gemma 3 4B | Yi-34B | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 28.1 | 27.8 |
| Released | 2025-03-12 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 23 |
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-34B: 32.3 (#274)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Coding | 1230 | 1112 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Yi-34B: —
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Yi-34B leads
Gemma 3 4B: 13.2 (#335), Yi-34B: 21.2 (#226)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1104 |
| Epoch Capabilities Index | 116.02 | 117.39 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| BIG-Bench Hard | — | 71.7% |
Math Yi-34B leads
Gemma 3 4B: 16.8 (#292), Yi-34B: 21.6 (#282)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Math | 1239 | 1114 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Gemma 3 4B leads
Gemma 3 4B: 11.8 (#299), Yi-34B: 7.5 (#309)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| GPQA Diamond | 23.2% | 14.7% |
| LMArena Expert | 1223 | 1061 |
| Vectara Hallucination Rate | 6.4% | — |
| MMLU | — | 76.3% |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Yi-34B: 29.7 (#264)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1273 | 1079 |
| LMArena German | 1281 | 1042 |
| LMArena Russian | 1294 | 1050 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1081 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Spanish | — | 1070 |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.2 (#225), Yi-34B: 56.2 (#274)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1091 |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), Yi-34B: 33.2 (#264)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1273 | 1094 |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.0 (#239), Yi-34B: 34.1 (#273)
| Benchmark | Gemma 3 4B | Yi-34B |
|---|---|---|
| LMArena Text | 1291 | 1129 |
| LMArena Creative Writing | 1271 | 1108 |
| LMArena Multi-Turn | 1255 | 1113 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Yi-34B?
Gemma 3 4B and Yi-34B score almost the same on the Noometry Index (28.1 vs 27.8), so choose on price, context window or the category you care about most.
Is Gemma 3 4B or Yi-34B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 32.3 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Yi-34B share?
14 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Yi-34B has 23.