Model comparison
Granite 3.0 8b Instruct vs phi-3-medium 14B
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.1 to 29.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
MicrosoftSummary
- They share 2 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.0 8b Instruct leads 29.1 to 9.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 35.4% for Granite 3.0 8b Instruct and 48.7% for phi-3-medium 14B.
Side by side
| Granite 3.0 8b Instruct | phi-3-medium 14B | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 31.1 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Granite 3.0 8b Instruct: 29.1 (#297), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 29.3% | 37.6% |
| BigCodeBench Complete | 35.4% | 48.7% |
| LMArena Coding | 1113 | — |
Reasoning Not comparable
Granite 3.0 8b Instruct: 20.0 (#227), phi-3-medium 14B: —
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1092 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Granite 3.0 8b Instruct leads
Granite 3.0 8b Instruct: 30.3 (#211), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1143 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Granite 3.0 8b Instruct leads
Granite 3.0 8b Instruct: 29.1 (#233), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1087 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Granite 3.0 8b Instruct: 27.4 (#271), phi-3-medium 14B: —
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1037 | — |
| LMArena Chinese | 1063 | — |
| LMArena Russian | 1060 | — |
Instruction Following Not comparable
Granite 3.0 8b Instruct: 56.2 (#271), phi-3-medium 14B: —
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1088 | — |
Long Context Not comparable
Granite 3.0 8b Instruct: 34.0 (#247), phi-3-medium 14B: —
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1122 | — |
Writing & Preference Not comparable
Granite 3.0 8b Instruct: 31.2 (#280), phi-3-medium 14B: —
| Benchmark | Granite 3.0 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1096 | — |
| LMArena Creative Writing | 1071 | — |
| LMArena Multi-Turn | 1063 | — |
Frequently asked questions
Is Granite 3.0 8b Instruct better than phi-3-medium 14B?
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.1 to 29.1 on the Noometry Index.
Is Granite 3.0 8b Instruct or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 29.1 in the Noometry coding category.
How many benchmarks do Granite 3.0 8b Instruct and phi-3-medium 14B share?
2 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and phi-3-medium 14B has 13.