Model comparison
Granite 4.2 8B vs Olmo 3 32b Think
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 38.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 7 categories and Olmo 3 32b Think in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 35.0.
Side by side
| Granite 4.2 8B | Olmo 3 32b Think | |
|---|---|---|
| Provider | IBM | Allen Institute for AI (Ai2) |
| Noometry Index | 40.5 | 38.7 |
| Released | — | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.25 | — |
| Results tracked | 11 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 8B leads
Granite 4.2 8B: 40.5 (#137), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1380 | 1319 |
Reasoning Too close to call
Granite 4.2 8B: 26.6 (#131), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1302 |
Math Not comparable
Granite 4.2 8B: —, Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | — | 1316 |
Knowledge Granite 4.2 8B leads
Granite 4.2 8B: 38.4 (#145), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1384 | 1273 |
Multilingual Granite 4.2 8B leads
Granite 4.2 8B: 44.5 (#178), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1302 | 1255 |
| LMArena Chinese | 1366 | 1300 |
| LMArena Russian | 1285 | 1254 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
Instruction Following Granite 4.2 8B leads
Granite 4.2 8B: 68.7 (#184), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1301 | 1275 |
Long Context Too close to call
Granite 4.2 8B: 40.3 (#159), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1324 | 1296 |
Writing & Preference Too close to call
Granite 4.2 8B: 49.6 (#189), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Granite 4.2 8B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1320 | 1300 |
| LMArena Creative Writing | 1236 | 1256 |
| LMArena Multi-Turn | 1301 | 1290 |
Frequently asked questions
Is Granite 4.2 8B better than Olmo 3 32b Think?
Granite 4.2 8B is the stronger model overall, scoring 40.5 to 38.7 on the Noometry Index.
Is Granite 4.2 8B or Olmo 3 32b Think better for coding?
Granite 4.2 8B scores higher on coding benchmarks: 40.5 versus 38.6 in the Noometry coding category.
How many benchmarks do Granite 4.2 8B and Olmo 3 32b Think share?
11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Olmo 3 32b Think has 14.