Model comparison
Granite 3.1 8b Instruct vs Phi-2
Granite 3.1 8b Instruct has enough public results to be ranked (#256); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSide by side
| Granite 3.1 8b Instruct | Phi-2 | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 31.8 | — |
| Released | — | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 3.1 8b Instruct: 33.9 (#232), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Coding | 1186 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 23.9 (#113), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Not comparable
Granite 3.1 8b Instruct: 21.2 (#204), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1146 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Granite 3.1 8b Instruct: 30.4 (#210), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Math | 1152 | — |
Knowledge Not comparable
Granite 3.1 8b Instruct: 30.6 (#218), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Expert | 1142 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Granite 3.1 8b Instruct: 31.1 (#255), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |
Instruction Following Not comparable
Granite 3.1 8b Instruct: 58.9 (#254), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1131 | — |
Long Context Not comparable
Granite 3.1 8b Instruct: 35.2 (#236), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1162 | — |
Writing & Preference Not comparable
Granite 3.1 8b Instruct: 35.7 (#261), Phi-2: —
| Benchmark | Granite 3.1 8b Instruct | Phi-2 |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| LMArena Multi-Turn | 1108 | — |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Phi-2?
Granite 3.1 8b Instruct has enough public results to be ranked (#256); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Granite 3.1 8b Instruct and Phi-2 share?
0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Phi-2 has 11.