Model comparison
GPT-5.6 Luna vs Magistral Medium
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 35.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Magistral Medium 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 35.1.
- The biggest single-benchmark swing is ARC-AGI-1: 88% for GPT-5.6 Luna and 6.1% for Magistral Medium.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.6 | 35.2 |
| Released | 2026-07-09 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.20 | $5 |
| Results tracked | 52 | 22 |
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), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| SciCode | 53.6% | 39.2% |
| LMArena Coding | 1466 | 1319 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Magistral Medium: —
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| 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), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 59.5% | 0% |
| Kagi LLM Benchmark | 49.1% | 16.2% |
| ARC-AGI-1 | 88% | 6.1% |
| CritPt | 20.6% | 0.3% |
| LMArena Hard Prompts | 1451 | 1267 |
| SimpleBench | 46.8% | — |
| NYT Connections (extended) | 69.4% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.39 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Math | 1458 | 1250 |
| 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), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Expert | 1478 | 1223 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), Magistral Medium: —
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| 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), Magistral Medium: 39.6 (#224)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1417 | 1232 |
| LMArena Chinese | 1470 | 1227 |
| LMArena French | 1456 | 1267 |
| LMArena German | 1454 | 1248 |
| LMArena Japanese | 1411 | 1175 |
| LMArena Korean | 1415 | 1125 |
| LMArena Russian | 1428 | 1224 |
| LMArena Spanish | 1448 | 1271 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Magistral Medium: 66.0 (#211)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1437 | 1254 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Magistral Medium: 39.3 (#183)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1436 | 1295 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Magistral Medium: 46.3 (#219)
| Benchmark | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| LMArena Text | 1431 | 1255 |
| LMArena Creative Writing | 1396 | 1245 |
| LMArena Multi-Turn | 1434 | 1275 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Magistral Medium?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 35.2 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Magistral Medium?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Magistral Medium lists at $2 and $5.
Is GPT-5.6 Luna or Magistral Medium better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 39.1 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 Magistral Medium share?
22 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Magistral Medium has 22.