Model comparison
Granite 3.1 2b Instruct vs Phi 3 Mini 4k Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 27.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 3.1 2b Instruct leads 57.7 to 47.7.
Side by side
| Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 33.2 | 27.9 |
| Released | — | 2024-04-23 |
| 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), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1149 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 33.1 (#206), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1159 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.8 (#224), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1131 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 29.1 (#269), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1068 | 1021 |
| LMArena Chinese | 1139 | 1021 |
| LMArena Russian | 1063 | 1022 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |
Instruction Following Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 57.7 (#264), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1116 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 35.0 (#244), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1155 | 1044 |
Writing & Preference Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 34.1 (#274), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Granite 3.1 2b Instruct | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1127 | 1073 |
| LMArena Creative Writing | 1116 | 1037 |
| LMArena Multi-Turn | 1099 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Phi 3 Mini 4k Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 27.9 on the Noometry Index.
Is Granite 3.1 2b Instruct or Phi 3 Mini 4k Instruct better for coding?
Granite 3.1 2b Instruct scores higher on coding benchmarks: 33.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Phi 3 Mini 4k Instruct share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.