Model comparison
Llama2 70b Steerlm Chat vs StarCoder 2 3B
Llama2 70b Steerlm Chat has enough public results to be ranked (#265); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
NVIDIASummary
- The widest gap is in coding, where StarCoder 2 3B leads 32.9 to 29.3.
Side by side
| Llama2 70b Steerlm Chat | StarCoder 2 3B | |
|---|---|---|
| Provider | NVIDIA | NVIDIA |
| Noometry Index | 31.2 | 35.8 |
| Released | — | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Llama2 70b Steerlm Chat: 29.3 (#295), StarCoder 2 3B: 32.9
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 1025 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Llama2 70b Steerlm Chat: 19.1 (#245), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1047 | — |
| Epoch Capabilities Index | — | 88.01 |
| WinoGrande | — | 57.1% |
Math Not comparable
Llama2 70b Steerlm Chat: 28.8 (#223), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1072 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multilingual Not comparable
Llama2 70b Steerlm Chat: 28.9 (#265), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1064 | — |
Instruction Following Not comparable
Llama2 70b Steerlm Chat: 54.5 (#274), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1061 | — |
Long Context Not comparable
Llama2 70b Steerlm Chat: 30.4 (#283), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 998 | — |
Writing & Preference Not comparable
Llama2 70b Steerlm Chat: 31.8 (#278), StarCoder 2 3B: —
| Benchmark | Llama2 70b Steerlm Chat | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1098 | — |
| LMArena Creative Writing | 1091 | — |
| LMArena Multi-Turn | 1058 | — |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than StarCoder 2 3B?
Llama2 70b Steerlm Chat has enough public results to be ranked (#265); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Llama2 70b Steerlm Chat or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 29.3 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and StarCoder 2 3B share?
0 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and StarCoder 2 3B has 7.