Model comparison
Falcon-180B vs StarCoder 2 3B
Falcon-180B has enough public results to be ranked (#260); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
Technology Innovation Institute
NVIDIASummary
- They share 5 benchmarks with published results for both.
Side by side
| Falcon-180B | StarCoder 2 3B | |
|---|---|---|
| Provider | Technology Innovation Institute | NVIDIA |
| Noometry Index | 32.2 | 36.3 |
| Released | 2023-09-06 | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, StarCoder 2 3B: 33.5
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Falcon-180B: 19.1 (#269), StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 112.13 | 88.76 |
| WinoGrande | 87.1% | 57.1% |
| LMArena Hard Prompts | 1007 | — |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| GSM8K | 54.4% | 21.6% |
Knowledge Not comparable
Falcon-180B: —, StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 34.2% |
| MMLU | 70.6% | 36.6% |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Not comparable
Falcon-180B: 25.2 (#286), StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1000 | — |
Instruction Following Not comparable
Falcon-180B: 53.4 (#286), StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1047 | — |
Writing & Preference Not comparable
Falcon-180B: 29.1 (#295), StarCoder 2 3B: —
| Benchmark | Falcon-180B | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1054 | — |
| LMArena Creative Writing | 1089 | — |
| LMArena Multi-Turn | 1013 | — |
Frequently asked questions
Is Falcon-180B better than StarCoder 2 3B?
Falcon-180B has enough public results to be ranked (#260); StarCoder 2 3B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-180B and StarCoder 2 3B share?
5 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and StarCoder 2 3B has 7.