Model comparison
GPT-6 Luna vs MiMo-V2-Pro
GPT-6 Luna is the stronger model overall, scoring 45.1 to 42.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 3 categories and MiMo-V2-Pro in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Luna leads 54.7 to 43.4.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 25.8% for MiMo-V2-Pro.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-6 Luna | MiMo-V2-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 45.1 | 42.4 |
| Released | 2026-09-22 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $0.43 |
| Output $ / M tokens | $0.50 | $0.87 |
| Results tracked | 18 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), MiMo-V2-Pro: 43.4 (#76)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1583 | 1433 |
| LMArena Coding | 1448 | 1476 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| ALE-Bench | — | 785.17 |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), MiMo-V2-Pro: 21.3 (#200)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 68.7% | 25.8% |
| LMArena Hard Prompts | 1415 | 1457 |
| Thematic Generalization | — | 45.9% |
Math MiMo-V2-Pro leads
GPT-6 Luna: 35.6 (#140), MiMo-V2-Pro: 36.7 (#104)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1396 | 1447 |
Knowledge Too close to call
GPT-6 Luna: 40.1 (#110), MiMo-V2-Pro: 40.8 (#106)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1458 | 1479 |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), MiMo-V2-Pro: —
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual MiMo-V2-Pro leads
GPT-6 Luna: 51.0 (#111), MiMo-V2-Pro: 52.9 (#77)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1390 | 1416 |
| LMArena Chinese | 1425 | 1455 |
| LMArena Russian | 1392 | 1427 |
| LMArena Spanish | 1416 | 1458 |
| LMArena French | — | 1470 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
| LMArena Korean | — | 1401 |
Instruction Following MiMo-V2-Pro leads
GPT-6 Luna: 74.7 (#85), MiMo-V2-Pro: 76.2 (#46)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1414 | 1444 |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.3 (#95), MiMo-V2-Pro: 41.5 (#133)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1417 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
GPT-6 Luna: 58.4 (#115), MiMo-V2-Pro: 62.9 (#67)
| Benchmark | GPT-6 Luna | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1392 | 1436 |
| LMArena Creative Writing | 1357 | 1415 |
| LMArena Multi-Turn | 1400 | 1456 |
Frequently asked questions
Is GPT-6 Luna better than MiMo-V2-Pro?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 42.4 on the Noometry Index.
Which is cheaper, GPT-6 Luna or MiMo-V2-Pro?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is GPT-6 Luna or MiMo-V2-Pro better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 43.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-6 Luna and MiMo-V2-Pro share?
15 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and MiMo-V2-Pro has 23.