Model comparison
StarCoder 2 15B vs Yi-1.5-34B
Yi-1.5-34B has enough public results to be ranked (#286); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. StarCoder 2 15B scores higher in 1 category and Yi-1.5-34B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 15B leads 36.0 to 31.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 38.4% for StarCoder 2 15B and 43.8% for Yi-1.5-34B.
Side by side
| StarCoder 2 15B | Yi-1.5-34B | |
|---|---|---|
| Provider | NVIDIA | 01.AI |
| Noometry Index | 37.5 | 30.2 |
| Released | 2024-02-20 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
StarCoder 2 15B: 36.0, Yi-1.5-34B: 31.9 (#267)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Complete | 38.4% | 43.8% |
| BigCodeBench Instruct | — | 33.9% |
| LMArena Coding | — | 1169 |
| HumanEval+ | 37.8% | — |
Reasoning Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 21.5 (#195)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | — | 1160 |
| Epoch Capabilities Index | 104.61 | — |
| WinoGrande | 64.3% | — |
Math Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 25.3 (#248)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | — | 1182 |
| MATH Level 5 | — | 25.5% |
| GSM8K | 57.7% | — |
Knowledge Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 14.8 (#290)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | — | 32% |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 47.2% | — |
| MMLU | 64.1% | — |
Multilingual Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 32.5 (#251)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | — | 1121 |
| LMArena Chinese | — | 1213 |
| LMArena French | — | 1155 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Russian | — | 1091 |
| LMArena Spanish | — | 1120 |
Instruction Following Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 59.4 (#252)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | — | 1139 |
Long Context Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 34.6 (#243)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | — | 1144 |
Writing & Preference Not comparable
StarCoder 2 15B: —, Yi-1.5-34B: 37.6 (#252)
| Benchmark | StarCoder 2 15B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | — | 1173 |
| LMArena Creative Writing | — | 1135 |
| LMArena Multi-Turn | — | 1153 |
Frequently asked questions
Is StarCoder 2 15B better than Yi-1.5-34B?
Yi-1.5-34B has enough public results to be ranked (#286); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is StarCoder 2 15B or Yi-1.5-34B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 31.9 in the Noometry coding category.
How many benchmarks do StarCoder 2 15B and Yi-1.5-34B share?
1 benchmark has published results for both models. StarCoder 2 15B has 7 scored results on Noometry and Yi-1.5-34B has 21.