Model comparison
GPT-6 Luna vs MiMo-V2-Flash
GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GPT-6 Luna scores higher in 5 categories and MiMo-V2-Flash in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.3.
- The biggest single-benchmark swing is SciCode: 54.6% for GPT-6 Luna and 25.9% for MiMo-V2-Flash.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.10 / $0.50 for GPT-6 Luna.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- MiMo-V2-Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | MiMo-V2-Flash | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 53.3 | 41.3 |
| Released | 2026-09-22 | 2025-12-16 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.14 |
| Output $ / M tokens | $0.50 | $0.28 |
| Results tracked | 42 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), MiMo-V2-Flash: 36.1 (#211)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena WebDev | 1581 | 1330 |
| SciCode | 54.6% | 25.9% |
| LMArena Coding | 1439 | 1443 |
| ALE-Bench | 1,577 | 737.95 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
Agentic & Tool Use Not comparable
GPT-6 Luna: 33.3 (#54), MiMo-V2-Flash: —
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| APEX-Agents | 44.3% | — |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), MiMo-V2-Flash: 24.9 (#157)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| CritPt | 19.4% | 0% |
| LMArena Hard Prompts | 1411 | 1420 |
| ARC-AGI-2 | 59.3% | — |
| NYT Connections (extended) | 68.7% | — |
| ARC-AGI-1 | 86.7% | — |
| Chess Puzzles | 31% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 90.1% | — |
| LMCA | 44.5% | — |
| Epoch Capabilities Index | 156.28 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), MiMo-V2-Flash: 38.3 (#139)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1416 | 1396 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 64% | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), MiMo-V2-Flash: 39.7 (#131)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1444 | 1425 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
Multimodal Not comparable
GPT-6 Luna: 42.4 (#30), MiMo-V2-Flash: —
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Vision | 1217 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual Too close to call
GPT-6 Luna: 50.5 (#117), MiMo-V2-Flash: 51.0 (#113)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1386 | 1392 |
| LMArena Chinese | 1433 | 1462 |
| LMArena French | 1420 | 1429 |
| LMArena German | 1369 | 1395 |
| LMArena Japanese | 1369 | 1325 |
| LMArena Korean | 1360 | 1358 |
| LMArena Russian | 1394 | 1387 |
| LMArena Spanish | 1393 | 1420 |
Instruction Following Too close to call
GPT-6 Luna: 74.3 (#99), MiMo-V2-Flash: 73.5 (#120)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1409 | 1392 |
Long Context Too close to call
GPT-6 Luna: 43.0 (#111), MiMo-V2-Flash: 43.0 (#110)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1409 | 1409 |
Writing & Preference MiMo-V2-Flash leads
GPT-6 Luna: 58.3 (#119), MiMo-V2-Flash: 59.7 (#106)
| Benchmark | GPT-6 Luna | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1391 | 1411 |
| LMArena Creative Writing | 1363 | 1375 |
| LMArena Multi-Turn | 1396 | 1404 |
Frequently asked questions
Is GPT-6 Luna better than MiMo-V2-Flash?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 41.3 on the Noometry Index.
Which is cheaper, GPT-6 Luna or MiMo-V2-Flash?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; GPT-6 Luna lists at $0.10 and $0.50.
Is GPT-6 Luna or MiMo-V2-Flash better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Luna and MiMo-V2-Flash share?
21 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and MiMo-V2-Flash has 21.