Model comparison
Granite 3.1 2b Instruct vs o3
o3 is the stronger model overall, scoring 47.5 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 o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o3 leads 63.5 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 | o3 | |
|---|---|---|
| Provider | IBM | OpenAI |
| Noometry Index | 33.2 | 47.5 |
| Released | — | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 12 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Granite 3.1 2b Instruct: 33.4 (#257), o3: 46.8 (#64)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Coding | 1149 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Granite 3.1 2b Instruct: —, o3: 34.5 (#44)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Granite 3.1 2b Instruct: 22.0 (#209), o3: 32.0 (#78)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
Granite 3.1 2b Instruct: 33.1 (#206), o3: 50.2 (#58)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Math | 1159 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Granite 3.1 2b Instruct: 30.8 (#224), o3: 54.6 (#52)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Expert | 1131 | 1402 |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, o3: 41.4 (#36)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Granite 3.1 2b Instruct: 29.1 (#269), o3: 51.7 (#105)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Non-English | 1068 | 1401 |
| LMArena Chinese | 1139 | 1437 |
| LMArena Russian | 1063 | 1406 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Spanish | — | 1395 |
Instruction Following o3 leads
Granite 3.1 2b Instruct: 57.7 (#264), o3: 72.8 (#127)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Granite 3.1 2b Instruct: 35.0 (#244), o3: 53.3 (#6)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Longer Query | 1155 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Granite 3.1 2b Instruct: 34.1 (#274), o3: 63.5 (#64)
| Benchmark | Granite 3.1 2b Instruct | o3 |
|---|---|---|
| LMArena Text | 1127 | 1410 |
| LMArena Creative Writing | 1116 | 1359 |
| LMArena Multi-Turn | 1099 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than o3?
o3 is the stronger model overall, scoring 47.5 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and o3 share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and o3 has 63.