Model comparison
GPT-6 Luna vs Llama 3.2 90B
GPT-6 Luna is the stronger model overall, scoring 53.3 to 27.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. GPT-6 Luna scores higher in 5 categories and Llama 3.2 90B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Llama 3.2 90B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 53.3 | 27.5 |
| Released | 2026-09-22 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 42 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-6 Luna: 55.5 (#25), Llama 3.2 90B: —
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 54.6% | — |
| LMArena Coding | 1439 | — |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use GPT-6 Luna leads
GPT-6 Luna: 33.3 (#54), Llama 3.2 90B: 30.0 (#80)
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| APEX-Agents | 44.3% | — |
| BALROG | — | 27.3% |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Llama 3.2 90B: 21.7 (#217)
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 156.28 | 125.5 |
| ARC-AGI-2 | 59.3% | — |
| NYT Connections (extended) | 68.7% | — |
| ARC-AGI-1 | 86.7% | — |
| CritPt | 19.4% | — |
| Chess Puzzles | 31% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1411 | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 90.1% | — |
| LMCA | 44.5% | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Llama 3.2 90B: 11.1 (#308)
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 2.6% |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| ProofBench | 64% | — |
| LMArena Math | 1416 | — |
| MATH Level 5 | — | 39.4% |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Llama 3.2 90B: 21.7 (#274)
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 90.5% | 41% |
| SimpleQA Verified | 41.4% | — |
| LMArena Expert | 1444 | — |
| MMLU | — | 80.3% |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.4 (#30), Llama 3.2 90B: 25.4 (#124)
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | 1217 | 1000 |
| GeoBench | — | 52% |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual Not comparable
GPT-6 Luna: 50.5 (#117), Llama 3.2 90B: —
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1386 | — |
| LMArena Chinese | 1433 | — |
| LMArena French | 1420 | — |
| LMArena German | 1369 | — |
| LMArena Japanese | 1369 | — |
| LMArena Korean | 1360 | — |
| LMArena Russian | 1394 | — |
| LMArena Spanish | 1393 | — |
Instruction Following Not comparable
GPT-6 Luna: 74.3 (#99), Llama 3.2 90B: —
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1409 | — |
Long Context Not comparable
GPT-6 Luna: 43.0 (#111), Llama 3.2 90B: —
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1409 | — |
Writing & Preference Not comparable
GPT-6 Luna: 58.3 (#119), Llama 3.2 90B: —
| Benchmark | GPT-6 Luna | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1391 | — |
| LMArena Creative Writing | 1363 | — |
| LMArena Multi-Turn | 1396 | — |
Frequently asked questions
Is GPT-6 Luna better than Llama 3.2 90B?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 27.5 on the Noometry Index.
How many benchmarks do GPT-6 Luna and Llama 3.2 90B share?
4 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Llama 3.2 90B has 9.