Model comparison
Granite 3.1 2b Instruct vs o1
o1 is the stronger model overall, scoring 40.9 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 0 categories and o1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1 leads 55.6 to 34.1.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 2b Instruct | o1 | |
|---|---|---|
| Provider | IBM | OpenAI |
| Noometry Index | 33.2 | 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 | 12 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Granite 3.1 2b Instruct: 33.4 (#257), o1: 46.1 (#70)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Coding | 1149 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, o1: 24.6 (#117)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Granite 3.1 2b Instruct: 22.0 (#209), o1: 27.9 (#111)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 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 o1 leads
Granite 3.1 2b Instruct: 33.1 (#206), o1: 36.1 (#175)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Math | 1159 | 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 3.1 2b Instruct: 30.8 (#224), o1: 41.5 (#110)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Expert | 1131 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, o1: 34.2 (#93)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Granite 3.1 2b Instruct: 29.1 (#269), o1: 48.6 (#142)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Non-English | 1068 | 1358 |
| LMArena Chinese | 1139 | 1394 |
| LMArena Russian | 1063 | 1356 |
| LMArena French | — | 1344 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Spanish | — | 1345 |
Instruction Following o1 leads
Granite 3.1 2b Instruct: 57.7 (#264), o1: 74.8 (#86)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Granite 3.1 2b Instruct: 35.0 (#244), o1: 50.3 (#9)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Longer Query | 1155 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Granite 3.1 2b Instruct: 34.1 (#274), o1: 55.6 (#144)
| Benchmark | Granite 3.1 2b Instruct | o1 |
|---|---|---|
| LMArena Text | 1127 | 1366 |
| LMArena Creative Writing | 1116 | 1348 |
| LMArena Multi-Turn | 1099 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than o1?
o1 is the stronger model overall, scoring 40.9 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and o1 share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and o1 has 52.