Model comparison
Granite 4.2 3b vs Olmo 2 0325 32b Instruct
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Granite 4.2 3b scores higher in 7 categories and Olmo 2 0325 32b Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 3b leads 35.6 to 19.2.
Side by side
| Granite 4.2 3b | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 39.0 | 32.2 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Granite 4.2 3b: 39.4 (#146), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1363 | 1210 |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 25.0 (#136), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1208 |
Math Not comparable
Granite 4.2 3b: —, Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | — | 16.1% |
| LMArena Math | — | 1208 |
Knowledge Granite 4.2 3b leads
Granite 4.2 3b: 35.6 (#169), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1313 | — |
Multilingual Granite 4.2 3b leads
Granite 4.2 3b: 42.4 (#193), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1160 |
| LMArena Chinese | 1268 | 1192 |
| LMArena Russian | 1249 | 1187 |
Instruction Following Granite 4.2 3b leads
Granite 4.2 3b: 67.2 (#195), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1271 | 1186 |
| IFEval | — | 78% |
Long Context Granite 4.2 3b leads
Granite 4.2 3b: 39.3 (#179), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1293 | 1194 |
Writing & Preference Granite 4.2 3b leads
Granite 4.2 3b: 47.9 (#202), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | Granite 4.2 3b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1295 | 1218 |
| LMArena Creative Writing | 1215 | 1199 |
| LMArena Multi-Turn | 1293 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is Granite 4.2 3b better than Olmo 2 0325 32b Instruct?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 32.2 on the Noometry Index.
Is Granite 4.2 3b or Olmo 2 0325 32b Instruct better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 34.6 in the Noometry coding category.
How many benchmarks do Granite 4.2 3b and Olmo 2 0325 32b Instruct share?
10 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.