Model comparison
GPT-5.6 Luna vs Mistral Large 3
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 38.6 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 9 categories and Mistral Large 3 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 36.0.
- The biggest single-benchmark swing is NYT Connections (extended): 69.4% for GPT-5.6 Luna and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 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.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.7 | 38.6 |
| Released | 2026-07-09 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.20 | $0.25 |
| Output $ / M tokens | $1.20 | $0.75 |
| Results tracked | 51 | 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: 53.9 (#25), Mistral Large 3: 34.1 (#230)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1517 | 1230 |
| LMArena Coding | 1466 | 1447 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 35.3 (#37), Mistral Large 3: —
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.5 (#38), Mistral Large 3: 14.6 (#314)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | 50.9% |
| NYT Connections (extended) | 69.4% | 7.5% |
| LMArena Hard Prompts | 1452 | 1429 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 23% |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.32 | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.5 (#12), Mistral Large 3: 36.0 (#131)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1455 | 1415 |
| 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: 58.6 (#31), Mistral Large 3: 35.5 (#173)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1479 | 1421 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal GPT-5.6 Luna leads
GPT-5.6 Luna: 43.0 (#22), Mistral Large 3: 37.6 (#65)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1259 | 1222 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual Too close to call
GPT-5.6 Luna: 53.0 (#73), Mistral Large 3: 52.6 (#79)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1418 | 1412 |
| LMArena Chinese | 1469 | 1448 |
| LMArena French | 1457 | 1456 |
| LMArena German | 1459 | 1438 |
| LMArena Japanese | 1416 | 1399 |
| LMArena Korean | 1414 | 1384 |
| LMArena Russian | 1428 | 1412 |
| LMArena Spanish | 1445 | 1437 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 76.0 (#48), Mistral Large 3: 74.1 (#104)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1440 | 1402 |
Long Context Too close to call
GPT-5.6 Luna: 43.9 (#78), Mistral Large 3: 43.1 (#102)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1437 | 1413 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.3 (#27), Mistral Large 3: 60.2 (#100)
| Benchmark | GPT-5.6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1432 | 1427 |
| LMArena Creative Writing | 1397 | 1385 |
| EQ-Bench Creative Writing | 1829 | 1412 |
| LMArena Multi-Turn | 1433 | 1429 |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Mistral Large 3?
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 38.6 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-5.6 Luna lists at $0.20 and $1.20.
Is GPT-5.6 Luna or Mistral Large 3 better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 53.9 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 Mistral Large 3 share?
22 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Mistral Large 3 has 24.