Model comparison
GPT-5.6 Luna vs MiniMax-M2.5
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 38.3 on the Noometry Index.
Last verified . 27 shared benchmarks.
MiniMaxSummary
- They share 27 benchmarks with published results for both. GPT-5.6 Luna scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 26.9.
- The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 4% for MiniMax-M2.5.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | MiniMax-M2.5 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 54.6 | 38.3 |
| Released | 2026-07-09 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.20 | $0.30 |
| Output $ / M tokens | $1.20 | $1.20 |
| Results tracked | 52 | 33 |
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), MiniMax-M2.5: 48.1 (#58)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1519 | 1387 |
| LMArena Coding | 1466 | 1381 |
| ALE-Bench | 1,667 | 618.17 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| CursorBench | 35.9% | — |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
Agentic & Tool Use GPT-5.6 Luna leads
GPT-5.6 Luna: 34.4 (#45), MiniMax-M2.5: 30.4 (#77)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| Vending-Bench 2 | 4,095 | -23.16 |
| Terminal-Bench | — | 42.7% |
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), MiniMax-M2.5: 17.5 (#292)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 59.5% | 4.9% |
| Kagi LLM Benchmark | 49.1% | 55.2% |
| NYT Connections (extended) | 69.4% | 16.8% |
| ARC-AGI-1 | 88% | 63.7% |
| LMArena Hard Prompts | 1451 | 1372 |
| Epoch Capabilities Index | 156.39 | 146.68 |
| SimpleBench | 46.8% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), MiniMax-M2.5: 26.9 (#253)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 60% | 4% |
| LMArena Math | 1458 | 1378 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), MiniMax-M2.5: 39.2 (#135)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1478 | 1379 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
GPT-5.6 Luna: 42.7 (#28), MiniMax-M2.5: —
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| 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), MiniMax-M2.5: 47.1 (#152)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1417 | 1338 |
| LMArena Chinese | 1470 | 1393 |
| LMArena French | 1456 | 1362 |
| LMArena German | 1454 | 1362 |
| LMArena Japanese | 1411 | 1171 |
| LMArena Korean | 1415 | 1232 |
| LMArena Russian | 1428 | 1358 |
| LMArena Spanish | 1448 | 1354 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), MiniMax-M2.5: 71.5 (#148)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1353 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), MiniMax-M2.5: 37.5 (#216)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1436 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), MiniMax-M2.5: 53.9 (#153)
| Benchmark | GPT-5.6 Luna | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1431 | 1359 |
| LMArena Creative Writing | 1396 | 1331 |
| EQ-Bench Creative Writing | 1829 | 1361 |
| LMArena Multi-Turn | 1434 | 1364 |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than MiniMax-M2.5?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 38.3 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or MiniMax-M2.5?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is GPT-5.6 Luna or MiniMax-M2.5 better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 48.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 205K.
How many benchmarks do GPT-5.6 Luna and MiniMax-M2.5 share?
27 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and MiniMax-M2.5 has 33.