# Granite 3.0 8b Instruct vs o3

> o3 is the stronger model overall, scoring 47.5 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-8b-instruct-vs-o3
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.0 8b 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 31.1.
- Granite 3.0 8b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| Provider | IBM | OpenAI |
| Noometry Index | 31.6 | 47.5 |
| Rank | 270 | 61 |
| Context | — | 200K |
| Input $/M | — | $2 |
| Output $/M | — | $8 |
| Weights | Open | Proprietary |

## Coding

- Granite 3.0 8b Instruct: 29.7 (#301)
- o3: 46.8 (#64)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Coding | 1112 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| BigCodeBench Instruct | 29.3% | — |
| BigCodeBench Complete | 35.4% | — |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |

## Agentic & Tool Use

- Granite 3.0 8b Instruct: —
- o3: 34.5 (#44)

| Benchmark | Granite 3.0 8b 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

- Granite 3.0 8b Instruct: 20.9 (#230)
- o3: 32.0 (#78)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Hard Prompts | 1092 | 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

- Granite 3.0 8b Instruct: 32.8 (#210)
- o3: 50.2 (#58)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Math | 1143 | 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

- Granite 3.0 8b Instruct: 29.6 (#236)
- o3: 54.6 (#52)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Expert | 1087 | 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

- Granite 3.0 8b Instruct: —
- o3: 41.4 (#36)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |

## Multilingual

- Granite 3.0 8b Instruct: 27.2 (#276)
- o3: 51.7 (#105)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Non-English | 1037 | 1401 |
| LMArena Chinese | 1063 | 1437 |
| LMArena Russian | 1060 | 1406 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Spanish | — | 1395 |

## Instruction Following

- Granite 3.0 8b Instruct: 56.0 (#276)
- o3: 72.8 (#127)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Instruction Following | 1088 | 1368 |
| IFEval | — | 86.9% |

## Long Context

- Granite 3.0 8b Instruct: 34.0 (#252)
- o3: 53.3 (#6)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Longer Query | 1122 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- Granite 3.0 8b Instruct: 31.1 (#285)
- o3: 63.5 (#64)

| Benchmark | Granite 3.0 8b Instruct | o3 |
|---|---|---|
| LMArena Text | 1096 | 1410 |
| LMArena Creative Writing | 1071 | 1359 |
| LMArena Multi-Turn | 1063 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |

## FAQ

### Is Granite 3.0 8b Instruct better than o3?

o3 is the stronger model overall, scoring 47.5 to 31.6 on the Noometry Index.

### Is Granite 3.0 8b Instruct or o3 better for coding?

o3 scores higher on coding benchmarks: 46.8 versus 29.7 in the Noometry coding category.

### How many benchmarks do Granite 3.0 8b Instruct and o3 share?

12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and o3 has 63.