Model comparison
GPT-5.6 Luna vs MiMo-V2.6-Flash
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 44.4 on the Noometry Index. MiMo-V2.6-Flash costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GPT-5.6 Luna scores higher in 6 categories and MiMo-V2.6-Flash in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 37.4.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 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 1.05M.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 54.7 | 44.4 |
| Released | 2026-07-09 | 2026-09-22 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.20 | $0.14 |
| Output $ / M tokens | $1.20 | $0.28 |
| Results tracked | 51 | 13 |
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), MiMo-V2.6-Flash: 44.3 (#68)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Coding | 1466 | 1516 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1517 | — |
| SciCode | 53.6% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 35.3 (#37), MiMo-V2.6-Flash: —
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| 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), MiMo-V2.6-Flash: 29.6 (#82)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1481 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| CritPt | 20.6% | — |
| Chess Puzzles | 40% | — |
| 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), MiMo-V2.6-Flash: 37.4 (#97)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1455 | 1477 |
| 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), MiMo-V2.6-Flash: 42.0 (#91)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1479 | 1516 |
| GPQA Diamond | 91.6% | — |
| SimpleQA Verified | 41% | — |
Multimodal GPT-5.6 Luna leads
GPT-5.6 Luna: 43.0 (#22), MiMo-V2.6-Flash: 40.2 (#39)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | 1259 | 1266 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual MiMo-V2.6-Flash leads
GPT-5.6 Luna: 53.0 (#73), MiMo-V2.6-Flash: 54.6 (#41)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1418 | 1439 |
| LMArena Chinese | 1469 | 1501 |
| LMArena Russian | 1428 | 1424 |
| LMArena French | 1457 | — |
| LMArena German | 1459 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1414 | — |
| LMArena Spanish | 1445 | — |
Instruction Following MiMo-V2.6-Flash leads
GPT-5.6 Luna: 76.0 (#48), MiMo-V2.6-Flash: 77.0 (#33)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1440 | 1463 |
Long Context Too close to call
GPT-5.6 Luna: 43.9 (#78), MiMo-V2.6-Flash: 44.8 (#52)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1437 | 1465 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.3 (#27), MiMo-V2.6-Flash: 63.9 (#61)
| Benchmark | GPT-5.6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1432 | 1459 |
| LMArena Creative Writing | 1397 | 1408 |
| LMArena Multi-Turn | 1433 | 1460 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than MiMo-V2.6-Flash?
GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 44.4 on the Noometry Index. MiMo-V2.6-Flash costs 2.6× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Luna or MiMo-V2.6-Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-5.6 Luna lists at $0.20 and $1.20.
Is GPT-5.6 Luna or MiMo-V2.6-Flash better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-5.6 Luna and MiMo-V2.6-Flash share?
13 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and MiMo-V2.6-Flash has 13.