Model comparison
Granite 3.1 8b Instruct vs phi-3-medium 14B
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 31.1 to 9.1.
Side by side
| Granite 3.1 8b Instruct | phi-3-medium 14B | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 32.4 | 29.7 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Granite 3.1 8b Instruct: 34.5 (#233), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1186 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Not comparable
Granite 3.1 8b Instruct: 22.1 (#207), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1145 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1152 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#220), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1142 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Granite 3.1 8b Instruct: 30.9 (#260), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |
Instruction Following Not comparable
Granite 3.1 8b Instruct: 58.6 (#259), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1131 | — |
Long Context Not comparable
Granite 3.1 8b Instruct: 35.2 (#241), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1162 | — |
Writing & Preference Not comparable
Granite 3.1 8b Instruct: 35.5 (#266), phi-3-medium 14B: —
| Benchmark | Granite 3.1 8b Instruct | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| LMArena Multi-Turn | 1108 | — |
Frequently asked questions
Is Granite 3.1 8b Instruct better than phi-3-medium 14B?
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 29.7 on the Noometry Index.
Is Granite 3.1 8b Instruct or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and phi-3-medium 14B share?
0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and phi-3-medium 14B has 13.