Model comparison
Granite 3.1 2b Instruct vs Llama 2-70B
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 24.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 2b Instruct leads 33.1 to 8.1.
Side by side
| Granite 3.1 2b Instruct | Llama 2-70B | |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 33.2 | 24.4 |
| Released | — | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.4 (#257), Llama 2-70B: 31.4 (#286)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1149 | 1079 |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Llama 2-70B: 14.4 (#325)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.79 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.1 (#206), Llama 2-70B: 8.1 (#326)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Math | 1159 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.8 (#224), Llama 2-70B: 7.4 (#310)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1131 | 1039 |
| GPQA Diamond | — | 26.3% |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 29.1 (#269), Llama 2-70B: 27.7 (#274)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1068 | 1045 |
| LMArena Chinese | 1139 | 995 |
| LMArena Russian | 1063 | 1083 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Spanish | — | 1143 |
Instruction Following Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 57.7 (#264), Llama 2-70B: 54.9 (#278)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1071 |
Long Context Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 35.0 (#244), Llama 2-70B: 32.3 (#270)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1155 | 1062 |
Writing & Preference Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 34.1 (#274), Llama 2-70B: 32.3 (#279)
| Benchmark | Granite 3.1 2b Instruct | Llama 2-70B |
|---|---|---|
| LMArena Text | 1127 | 1115 |
| LMArena Creative Writing | 1116 | 1075 |
| LMArena Multi-Turn | 1099 | 1088 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Llama 2-70B?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 24.4 on the Noometry Index.
Is Granite 3.1 2b Instruct or Llama 2-70B better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 33.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Llama 2-70B share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Llama 2-70B has 35.