Model comparison
Granite 4.1 8b vs Phi 3 Small 8k Instruct
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 29.3 on the Noometry Index.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.1 8b leads 48.1 to 31.1.
Side by side
| Granite 4.1 8b | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 37.4 | 29.3 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.1 8b leads
Granite 4.1 8b: 30.1 (#297), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1312 | 1101 |
| LMArena WebDev | 1192 | — |
| LiveBench Coding | — | 20.3% |
Reasoning Granite 4.1 8b leads
Granite 4.1 8b: 25.7 (#143), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Granite 4.1 8b leads
Granite 4.1 8b: 36.4 (#166), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1312 | 1151 |
| LiveBench Math | — | 17.6% |
Knowledge Granite 4.1 8b leads
Granite 4.1 8b: 36.1 (#174), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1309 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Granite 4.1 8b leads
Granite 4.1 8b: 41.7 (#204), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1261 | 1058 |
| LMArena Chinese | 1337 | 1061 |
| LMArena Russian | 1240 | 1111 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Spanish | — | 1111 |
Instruction Following Granite 4.1 8b leads
Granite 4.1 8b: 66.9 (#203), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1269 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Granite 4.1 8b leads
Granite 4.1 8b: 38.7 (#193), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1275 | 1088 |
Writing & Preference Granite 4.1 8b leads
Granite 4.1 8b: 48.1 (#204), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Granite 4.1 8b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1290 | 1110 |
| LMArena Creative Writing | 1251 | 1083 |
| LMArena Multi-Turn | 1268 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Granite 4.1 8b better than Phi 3 Small 8k Instruct?
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 29.3 on the Noometry Index.
Is Granite 4.1 8b or Phi 3 Small 8k Instruct better for coding?
Granite 4.1 8b scores higher on coding benchmarks: 30.1 versus 27.9 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Phi 3 Small 8k Instruct share?
12 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Phi 3 Small 8k Instruct has 32.