Model comparison
Gemma 3 12B vs Yi-1.5-34B
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.6 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Yi-1.5-34B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 32.3.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 32% for Yi-1.5-34B.
Side by side
| Gemma 3 12B | Yi-1.5-34B | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 32.1 | 30.6 |
| Released | 2025-03-12 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 12B: 31.7 (#280), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1281 | 1169 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Yi-1.5-34B: —
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Yi-1.5-34B leads
Gemma 3 12B: 15.7 (#313), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1160 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Yi-1.5-34B leads
Gemma 3 12B: 22.3 (#279), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1307 | 1182 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| MATH Level 5 | — | 25.5% |
Knowledge Gemma 3 12B leads
Gemma 3 12B: 26.5 (#257), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 39.5% | 32% |
| LMArena Expert | 1248 | 1144 |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Yi-1.5-34B: —
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1318 | 1121 |
| LMArena German | 1370 | 1111 |
| LMArena Russian | 1335 | 1091 |
| LMArena Chinese | — | 1213 |
| LMArena French | — | 1156 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Spanish | — | 1121 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1139 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1317 | 1143 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Gemma 3 12B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1334 | 1173 |
| LMArena Creative Writing | 1331 | 1135 |
| LMArena Multi-Turn | 1334 | 1153 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Yi-1.5-34B?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.6 on the Noometry Index.
Is Gemma 3 12B or Yi-1.5-34B better for coding?
They score almost the same on coding (31.7 vs 32.4); test both on your own repository before choosing.
How many benchmarks do Gemma 3 12B and Yi-1.5-34B share?
13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Yi-1.5-34B has 21.