Model comparison
Llama 3.1 Tulu 3 8b vs StarCoder 2 15B
Llama 3.1 Tulu 3 8b has enough public results to be ranked (#220); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)
NVIDIASide by side
| Llama 3.1 Tulu 3 8b | StarCoder 2 15B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | NVIDIA |
| Noometry Index | 35.1 | 37.5 |
| Released | — | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
Llama 3.1 Tulu 3 8b: 33.9 (#235), StarCoder 2 15B: 36.0
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Coding | 1184 | — |
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
Llama 3.1 Tulu 3 8b: 21.8 (#188), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Hard Prompts | 1174 | — |
| Epoch Capabilities Index | — | 104.61 |
| WinoGrande | — | 64.3% |
Math Not comparable
Llama 3.1 Tulu 3 8b: 31.3 (#196), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Math | 1195 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Llama 3.1 Tulu 3 8b: —, StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multilingual Not comparable
Llama 3.1 Tulu 3 8b: 35.6 (#241), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1169 | — |
| LMArena Chinese | 1175 | — |
| LMArena Russian | 1193 | — |
Instruction Following Not comparable
Llama 3.1 Tulu 3 8b: 61.6 (#241), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1174 | — |
Long Context Not comparable
Llama 3.1 Tulu 3 8b: 35.8 (#234), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1181 | — |
Writing & Preference Not comparable
Llama 3.1 Tulu 3 8b: 39.9 (#240), StarCoder 2 15B: —
| Benchmark | Llama 3.1 Tulu 3 8b | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1193 | — |
| LMArena Creative Writing | 1182 | — |
| LMArena Multi-Turn | 1154 | — |
Frequently asked questions
Is Llama 3.1 Tulu 3 8b better than StarCoder 2 15B?
Llama 3.1 Tulu 3 8b has enough public results to be ranked (#220); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Llama 3.1 Tulu 3 8b or StarCoder 2 15B better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 33.9 in the Noometry coding category.
How many benchmarks do Llama 3.1 Tulu 3 8b and StarCoder 2 15B share?
0 benchmarks have published results for both models. Llama 3.1 Tulu 3 8b has 11 scored results on Noometry and StarCoder 2 15B has 7.