Model comparison
Granite 4.1 8b vs o1
o1 is the stronger model overall, scoring 40.9 to 37.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 1 category and o1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where o1 leads 46.1 to 30.1.
- Granite 4.1 8b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.1 8b | o1 | |
|---|---|---|
| Provider | IBM | OpenAI |
| Noometry Index | 37.4 | 40.9 |
| Released | — | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 13 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Granite 4.1 8b: 30.1 (#297), o1: 46.1 (#70)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Coding | 1312 | 1367 |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1192 | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Granite 4.1 8b: —, o1: 24.6 (#117)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Granite 4.1 8b: 25.7 (#143), o1: 27.9 (#111)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1371 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.91 |
| LiveBench | — | 75.7% |
Math Too close to call
Granite 4.1 8b: 36.4 (#166), o1: 36.1 (#175)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Math | 1312 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Granite 4.1 8b: 36.1 (#174), o1: 41.5 (#110)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Expert | 1309 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
Granite 4.1 8b: —, o1: 34.2 (#93)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Granite 4.1 8b: 41.7 (#204), o1: 48.6 (#142)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Non-English | 1261 | 1358 |
| LMArena Chinese | 1337 | 1394 |
| LMArena Russian | 1240 | 1356 |
| LMArena French | — | 1344 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Spanish | — | 1345 |
Instruction Following o1 leads
Granite 4.1 8b: 66.9 (#203), o1: 74.8 (#86)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Instruction Following | 1269 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Granite 4.1 8b: 38.7 (#193), o1: 50.3 (#9)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Longer Query | 1275 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Granite 4.1 8b: 48.1 (#204), o1: 55.6 (#144)
| Benchmark | Granite 4.1 8b | o1 |
|---|---|---|
| LMArena Text | 1290 | 1366 |
| LMArena Creative Writing | 1251 | 1348 |
| LMArena Multi-Turn | 1268 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Granite 4.1 8b better than o1?
o1 is the stronger model overall, scoring 40.9 to 37.4 on the Noometry Index.
Is Granite 4.1 8b or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 30.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and o1 share?
12 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and o1 has 52.