Model comparison
Granite 3.1 8b Instruct vs Granite 4.1 8b
Granite 4.1 8b is the stronger model overall, scoring 36.8 to 31.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and Granite 4.1 8b in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.1 8b leads 48.3 to 35.7.
Side by side
| Granite 3.1 8b Instruct | Granite 4.1 8b | |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 31.8 | 36.8 |
| Released | — | — |
| 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 Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.9 (#232), Granite 4.1 8b: 29.9 (#291)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Coding | 1186 | 1313 |
| LMArena WebDev | — | 1190 |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 23.9 (#113), Granite 4.1 8b: —
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Granite 4.1 8b leads
Granite 3.1 8b Instruct: 21.2 (#204), Granite 4.1 8b: 24.6 (#142)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1294 |
Math Granite 4.1 8b leads
Granite 3.1 8b Instruct: 30.4 (#210), Granite 4.1 8b: 33.8 (#167)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Math | 1152 | 1311 |
Knowledge Granite 4.1 8b leads
Granite 3.1 8b Instruct: 30.6 (#218), Granite 4.1 8b: 35.5 (#171)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Expert | 1142 | 1310 |
Multilingual Granite 4.1 8b leads
Granite 3.1 8b Instruct: 31.1 (#255), Granite 4.1 8b: 41.8 (#199)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Non-English | 1099 | 1261 |
| LMArena Chinese | 1145 | 1335 |
| LMArena Russian | 1092 | 1238 |
Instruction Following Granite 4.1 8b leads
Granite 3.1 8b Instruct: 58.9 (#254), Granite 4.1 8b: 67.0 (#198)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Instruction Following | 1131 | 1268 |
Long Context Granite 4.1 8b leads
Granite 3.1 8b Instruct: 35.2 (#236), Granite 4.1 8b: 38.7 (#188)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Longer Query | 1162 | 1275 |
Writing & Preference Granite 4.1 8b leads
Granite 3.1 8b Instruct: 35.7 (#261), Granite 4.1 8b: 48.3 (#199)
| Benchmark | Granite 3.1 8b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Text | 1150 | 1291 |
| LMArena Creative Writing | 1129 | 1249 |
| LMArena Multi-Turn | 1108 | 1269 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Granite 4.1 8b?
Granite 4.1 8b is the stronger model overall, scoring 36.8 to 31.8 on the Noometry Index.
Is Granite 3.1 8b Instruct or Granite 4.1 8b better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 29.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and Granite 4.1 8b share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Granite 4.1 8b has 13.