Model comparison
Falcon-180B vs Granite 3.1 2b Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 32.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
Technology Innovation InstituteSummary
- They share 6 benchmarks with published results for both. Falcon-180B scores higher in 0 categories and Granite 3.1 2b Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 2b Instruct leads 34.1 to 29.1.
Side by side
| Falcon-180B | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Technology Innovation Institute | IBM |
| Noometry Index | 32.2 | 33.2 |
| Released | 2023-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Granite 3.1 2b Instruct: 33.4 (#257)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | — | 1149 |
Reasoning Granite 3.1 2b Instruct leads
Falcon-180B: 19.1 (#269), Granite 3.1 2b Instruct: 22.0 (#209)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1138 |
| Epoch Capabilities Index | 112.13 | — |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Granite 3.1 2b Instruct: 33.1 (#206)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | — | 1159 |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Granite 3.1 2b Instruct: 30.8 (#224)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1131 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 64.2% | — |
Multilingual Granite 3.1 2b Instruct leads
Falcon-180B: 25.2 (#286), Granite 3.1 2b Instruct: 29.1 (#269)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1000 | 1068 |
| LMArena Chinese | — | 1139 |
| LMArena Russian | — | 1063 |
Instruction Following Granite 3.1 2b Instruct leads
Falcon-180B: 53.4 (#286), Granite 3.1 2b Instruct: 57.7 (#264)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1047 | 1116 |
Long Context Not comparable
Falcon-180B: —, Granite 3.1 2b Instruct: 35.0 (#244)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1155 |
Writing & Preference Granite 3.1 2b Instruct leads
Falcon-180B: 29.1 (#295), Granite 3.1 2b Instruct: 34.1 (#274)
| Benchmark | Falcon-180B | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1054 | 1127 |
| LMArena Creative Writing | 1089 | 1116 |
| LMArena Multi-Turn | 1013 | 1099 |
Frequently asked questions
Is Falcon-180B better than Granite 3.1 2b Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 32.2 on the Noometry Index.
How many benchmarks do Falcon-180B and Granite 3.1 2b Instruct share?
6 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Granite 3.1 2b Instruct has 12.