Model comparison
Gemma 2 27B vs Yi-34B
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 2 27B scores higher in 6 categories and Yi-34B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 2 27B leads 19.0 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 5.1% for Yi-34B.
Side by side
| Gemma 2 27B | Yi-34B | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 29.4 | 27.8 |
| Released | 2024-06-24 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 34.1 (#246), Yi-34B: 32.3 (#274)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Coding | 1211 | 1112 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Yi-34B leads
Gemma 2 27B: 15.3 (#315), Yi-34B: 21.2 (#226)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1104 |
| Epoch Capabilities Index | 122.08 | 117.39 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| BIG-Bench Hard | — | 71.7% |
| LiveBench | 38.2% | — |
Math Yi-34B leads
Gemma 2 27B: 10.7 (#311), Yi-34B: 21.6 (#282)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Math | 1212 | 1114 |
| MATH Level 5 | 27.9% | 5.1% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| GSM8K | — | 76% |
Knowledge Gemma 2 27B leads
Gemma 2 27B: 19.0 (#280), Yi-34B: 7.5 (#309)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| GPQA Diamond | 36.5% | 14.7% |
| LMArena Expert | 1172 | 1061 |
| MMLU | 75.7% | 76.3% |
| Confabulations | 27.1% | — |
Multilingual Gemma 2 27B leads
Gemma 2 27B: 38.6 (#226), Yi-34B: 29.7 (#264)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1217 | 1079 |
| LMArena Chinese | 1221 | 1176 |
| LMArena French | 1247 | 1081 |
| LMArena German | 1209 | 1042 |
| LMArena Japanese | 1175 | 993 |
| LMArena Korean | 1174 | 959 |
| LMArena Russian | 1234 | 1050 |
| LMArena Spanish | 1228 | 1070 |
Instruction Following Gemma 2 27B leads
Gemma 2 27B: 60.5 (#249), Yi-34B: 56.2 (#274)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1091 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), Yi-34B: 33.2 (#264)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1231 | 1094 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Yi-34B: 34.1 (#273)
| Benchmark | Gemma 2 27B | Yi-34B |
|---|---|---|
| LMArena Text | 1231 | 1129 |
| LMArena Creative Writing | 1241 | 1108 |
| LMArena Multi-Turn | 1224 | 1113 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Yi-34B?
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.8 on the Noometry Index.
Is Gemma 2 27B or Yi-34B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 32.3 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Yi-34B share?
21 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Yi-34B has 23.