Model comparison
GPT-6 Luna vs Granite 3.1 2b Instruct
GPT-6 Luna is the stronger model overall, scoring 45.1 to 32.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Granite 3.1 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Luna leads 58.4 to 34.3.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 45.1 | 32.6 |
| Released | 2026-09-22 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 18 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), Granite 3.1 2b Instruct: 32.9 (#255)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1448 | 1149 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1583 | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), Granite 3.1 2b Instruct: 21.0 (#206)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1138 |
| NYT Connections (extended) | 68.7% | — |
Math GPT-6 Luna leads
GPT-6 Luna: 35.6 (#140), Granite 3.1 2b Instruct: 30.6 (#206)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1396 | 1159 |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 40.1 (#110), Granite 3.1 2b Instruct: 30.3 (#223)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1458 | 1131 |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Granite 3.1 2b Instruct: —
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 51.0 (#111), Granite 3.1 2b Instruct: 29.2 (#264)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1390 | 1068 |
| LMArena Chinese | 1425 | 1138 |
| LMArena Russian | 1392 | 1063 |
| LMArena Spanish | 1416 | — |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.7 (#85), Granite 3.1 2b Instruct: 58.0 (#259)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1414 | 1116 |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.3 (#95), Granite 3.1 2b Instruct: 35.0 (#239)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1417 | 1155 |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.4 (#115), Granite 3.1 2b Instruct: 34.3 (#269)
| Benchmark | GPT-6 Luna | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1392 | 1127 |
| LMArena Creative Writing | 1357 | 1116 |
| LMArena Multi-Turn | 1400 | 1099 |
Frequently asked questions
Is GPT-6 Luna better than Granite 3.1 2b Instruct?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 32.6 on the Noometry Index.
Is GPT-6 Luna or Granite 3.1 2b Instruct better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 32.9 in the Noometry coding category.
How many benchmarks do GPT-6 Luna and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Granite 3.1 2b Instruct has 12.