Model comparison
Granite 3.1 8b Instruct vs Phi 3 Mini 4k Instruct June 2024
Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 30.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 7 categories and Phi 3 Mini 4k Instruct June 2024 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 8b Instruct leads 35.7 to 29.7.
Side by side
| Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 31.8 | 30.7 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.9 (#232), Phi 3 Mini 4k Instruct June 2024: 31.2 (#275)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Coding | 1186 | 1093 |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 23.9 (#113), Phi 3 Mini 4k Instruct June 2024: —
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 21.2 (#204), Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1088 |
Math Too close to call
Granite 3.1 8b Instruct: 30.4 (#210), Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Math | 1152 | 1152 |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 30.6 (#218), Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Expert | 1142 | 1051 |
Multilingual Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#255), Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Non-English | 1099 | 1013 |
| LMArena Chinese | 1145 | 1033 |
| LMArena Russian | 1092 | 1019 |
| LMArena German | — | 1031 |
| LMArena Japanese | — | 954 |
| LMArena Korean | — | 880 |
Instruction Following Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 58.9 (#254), Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1058 |
Long Context Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 35.2 (#236), Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Longer Query | 1162 | 1042 |
Writing & Preference Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 35.7 (#261), Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)
| Benchmark | Granite 3.1 8b Instruct | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Text | 1150 | 1080 |
| LMArena Creative Writing | 1129 | 1045 |
| LMArena Multi-Turn | 1108 | 1049 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Phi 3 Mini 4k Instruct June 2024?
Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 30.7 on the Noometry Index.
Is Granite 3.1 8b Instruct or Phi 3 Mini 4k Instruct June 2024 better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 31.2 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Phi 3 Mini 4k Instruct June 2024 share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.