Model comparison
GPT-5.6 Luna vs Trinity Large Thinking
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 38.6 on the Noometry Index.
Last verified . 22 shared benchmarks.
Arcee AISummary
- They share 22 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 37.6.
- The biggest single-benchmark swing is NYT Connections (extended): 69.4% for GPT-5.6 Luna and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.20 / $1.20 for GPT-5.6 Luna.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 54.6 | 38.6 |
| Released | 2026-07-09 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 80K |
| Input $ / M tokens | $0.20 | $0.25 |
| Output $ / M tokens | $1.20 | $0.80 |
| Results tracked | 52 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1519 | 1238 |
| SciCode | 53.6% | 36.1% |
| LMArena Coding | 1466 | 1381 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Trinity Large Thinking: —
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 69.4% | 16.5% |
| CritPt | 20.6% | 0.9% |
| LMArena Hard Prompts | 1451 | 1350 |
| Surface Evolver Bench | 61.9% | 15.6% |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| ARC-AGI-1 | 88% | — |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Epoch Capabilities Index | 156.39 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1458 | 1366 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 60% | — |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1478 | 1360 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), Trinity Large Thinking: —
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1258 | — |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1417 | 1325 |
| LMArena Chinese | 1470 | 1373 |
| LMArena French | 1456 | 1374 |
| LMArena German | 1454 | 1356 |
| LMArena Japanese | 1411 | 1311 |
| LMArena Korean | 1415 | 1306 |
| LMArena Russian | 1428 | 1337 |
| LMArena Spanish | 1448 | 1357 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1437 | 1334 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1436 | 1355 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GPT-5.6 Luna | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1431 | 1340 |
| LMArena Creative Writing | 1396 | 1320 |
| LMArena Multi-Turn | 1434 | 1342 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Trinity Large Thinking?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 38.6 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; GPT-5.6 Luna lists at $0.20 and $1.20.
Is GPT-5.6 Luna or Trinity Large Thinking better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.6 Luna and Trinity Large Thinking share?
22 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Trinity Large Thinking has 24.