Model comparison
Granite 3.1 8b Instruct vs Phi-3.5-mini
Granite 3.1 8b Instruct has enough public results to be ranked (#258); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSide by side
| Granite 3.1 8b Instruct | Phi-3.5-mini | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 32.4 | 36.9 |
| Released | — | 2024-08-16 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 3.1 8b Instruct: 34.5 (#233), Phi-3.5-mini: 34.6 (#232)
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1186 | — |
| BigCodeBench Complete | — | 38.5% |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Not comparable
Granite 3.1 8b Instruct: 22.1 (#207), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Hard Prompts | 1145 | — |
| PIQA | — | 81% |
Math Not comparable
Granite 3.1 8b Instruct: 33.0 (#209), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Math | 1152 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Granite 3.1 8b Instruct: 31.1 (#220), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Expert | 1142 | — |
| BoolQ | — | 78% |
Multilingual Not comparable
Granite 3.1 8b Instruct: 30.9 (#260), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |
Instruction Following Not comparable
Granite 3.1 8b Instruct: 58.6 (#259), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1131 | — |
Long Context Not comparable
Granite 3.1 8b Instruct: 35.2 (#241), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1162 | — |
Writing & Preference Not comparable
Granite 3.1 8b Instruct: 35.5 (#266), Phi-3.5-mini: —
| Benchmark | Granite 3.1 8b Instruct | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| LMArena Multi-Turn | 1108 | — |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Phi-3.5-mini?
Granite 3.1 8b Instruct has enough public results to be ranked (#258); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Granite 3.1 8b Instruct or Phi-3.5-mini better for coding?
They score almost the same on coding (34.5 vs 34.6); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 8b Instruct and Phi-3.5-mini share?
0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Phi-3.5-mini has 5.