Model comparison
Falcon-40B vs StarCoder 2 15B
Neither Falcon-40B nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
Technology Innovation Institute
NVIDIASummary
- They share 5 benchmarks with published results for both.
Side by side
| Falcon-40B | StarCoder 2 15B | |
|---|---|---|
| Provider | Technology Innovation Institute | NVIDIA |
| Noometry Index | — | 38.1 |
| Released | 2023-03-15 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, StarCoder 2 15B: 36.6
| Benchmark | Falcon-40B | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
Falcon-40B: —, StarCoder 2 15B: —
| Benchmark | Falcon-40B | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 104.45 | 105 |
| WinoGrande | 76.9% | 64.3% |
| BIG-Bench Hard | 37.1% | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 77.3% | — |
| PIQA | 83% | — |
Math Not comparable
Falcon-40B: —, StarCoder 2 15B: —
| Benchmark | Falcon-40B | StarCoder 2 15B |
|---|---|---|
| GSM8K | 33.8% | 57.7% |
Knowledge Not comparable
Falcon-40B: —, StarCoder 2 15B: —
| Benchmark | Falcon-40B | StarCoder 2 15B |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 47.2% |
| MMLU | 56.9% | 64.1% |
| BoolQ | 83.1% | — |
| OpenBookQA | 56.6% | — |
| TriviaQA | 79.9% | — |
Frequently asked questions
Is Falcon-40B better than StarCoder 2 15B?
Neither Falcon-40B nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Falcon-40B and StarCoder 2 15B share?
5 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and StarCoder 2 15B has 7.