Model comparison
Gemma 3 27B vs Yi-34B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and Yi-34B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 34.1.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 5.1% for Yi-34B.
Side by side
| Gemma 3 27B | Yi-34B | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 30.8 | 27.8 |
| Released | 2025-03-11 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Gemma 3 27B: 22.5 (#334), Yi-34B: 32.3 (#274)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Coding | 1322 | 1112 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Yi-34B: —
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Yi-34B leads
Gemma 3 27B: 16.7 (#301), Yi-34B: 21.2 (#226)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1104 |
| Epoch Capabilities Index | 130.04 | 117.39 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| BIG-Bench Hard | — | 71.7% |
| LiveBench | 50% | — |
Math Gemma 3 27B leads
Gemma 3 27B: 25.9 (#265), Yi-34B: 21.6 (#282)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Math | 1312 | 1114 |
| MATH Level 5 | 74% | 5.1% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| GSM8K | — | 76% |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), Yi-34B: 7.5 (#309)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| GPQA Diamond | 47.7% | 14.7% |
| LMArena Expert | 1304 | 1061 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| MMLU | — | 76.3% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Yi-34B: —
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Yi-34B: 29.7 (#264)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1334 | 1079 |
| LMArena Chinese | 1346 | 1176 |
| LMArena French | 1368 | 1081 |
| LMArena German | 1362 | 1042 |
| LMArena Japanese | 1287 | 993 |
| LMArena Korean | 1308 | 959 |
| LMArena Russian | 1349 | 1050 |
| LMArena Spanish | 1349 | 1070 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Yi-34B: 56.2 (#274)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1091 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Yi-34B leads
Gemma 3 27B: 27.6 (#293), Yi-34B: 33.2 (#264)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1333 | 1094 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Yi-34B: 34.1 (#273)
| Benchmark | Gemma 3 27B | Yi-34B |
|---|---|---|
| LMArena Text | 1358 | 1129 |
| LMArena Creative Writing | 1346 | 1108 |
| LMArena Multi-Turn | 1345 | 1113 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Yi-34B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Is Gemma 3 27B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Yi-34B share?
20 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Yi-34B has 23.