Model comparison
Deepseek Coder v2 vs Yi-34B
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Deepseek Coder v2 leads 31.7 to 7.5.
Side by side
| Deepseek Coder v2 | Yi-34B | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 35.3 | 27.4 |
| Released | 2024-06-17 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 37.5 (#178), Yi-34B: 31.8 (#269)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Coding | 1251 | 1112 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 22.6 (#175), Yi-34B: 20.3 (#222)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.28 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#188), Yi-34B: 19.8 (#277)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Math | 1241 | 1114 |
| GSM8K | 94.5% | 76% |
| MATH Level 5 | — | 5.1% |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 31.7 (#209), Yi-34B: 7.5 (#304)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Expert | 1181 | 1061 |
| GPQA Diamond | — | 14.7% |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 76.3% |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.4 (#235), Yi-34B: 29.9 (#259)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1182 | 1079 |
| LMArena Chinese | 1201 | 1175 |
| LMArena French | 1184 | 1080 |
| LMArena German | 1164 | 1042 |
| LMArena Japanese | 1126 | 993 |
| LMArena Korean | 1104 | 959 |
| LMArena Russian | 1188 | 1050 |
| LMArena Spanish | 1153 | 1070 |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.9 (#237), Yi-34B: 56.4 (#269)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1091 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#219), Yi-34B: 33.2 (#259)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1219 | 1094 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.4 (#249), Yi-34B: 34.3 (#268)
| Benchmark | Deepseek Coder v2 | Yi-34B |
|---|---|---|
| LMArena Text | 1191 | 1129 |
| LMArena Creative Writing | 1120 | 1108 |
| LMArena Multi-Turn | 1176 | 1113 |
Frequently asked questions
Is Deepseek Coder v2 better than Yi-34B?
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 27.4 on the Noometry Index.
Is Deepseek Coder v2 or Yi-34B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 31.8 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Yi-34B share?
18 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Yi-34B has 23.