Model comparison
GPT-6 Luna vs MiMo-V2.6-Pro
GPT-6 Luna is the stronger model overall, scoring 53.3 to 50.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GPT-6 Luna scores higher in 4 categories and MiMo-V2.6-Pro in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 54.5.
- The biggest single-benchmark swing is APEX-Agents: 44.3% for GPT-6 Luna and 59.5% for MiMo-V2.6-Pro.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 53.3 | 50.3 |
| Released | 2026-09-22 | 2026-09-21 |
| Weights | Proprietary | Open |
| 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 | 42 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-6 Luna: 55.5 (#25), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1581 | 1629 |
| SciCode | 54.6% | 60.9% |
| LMArena Coding | 1439 | 1534 |
| ALE-Bench | 1,577 | 1,158 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
GPT-6 Luna: 33.3 (#54), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 44.3% | 59.5% |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 19.4% | 26.6% |
| LMArena Hard Prompts | 1411 | 1512 |
| 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-V2.6-Pro: 54.5 (#45)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 64% | 70% |
| LMArena Math | 1416 | 1494 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1444 | 1543 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.4 (#30), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1217 | 1264 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual MiMo-V2.6-Pro leads
GPT-6 Luna: 50.5 (#117), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1386 | 1474 |
| LMArena Chinese | 1433 | 1529 |
| LMArena Russian | 1394 | 1480 |
| LMArena French | 1420 | — |
| LMArena German | 1369 | — |
| LMArena Japanese | 1369 | — |
| LMArena Korean | 1360 | — |
| LMArena Spanish | 1393 | — |
Instruction Following MiMo-V2.6-Pro leads
GPT-6 Luna: 74.3 (#99), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1409 | 1493 |
Long Context MiMo-V2.6-Pro leads
GPT-6 Luna: 43.0 (#111), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1409 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
GPT-6 Luna: 58.3 (#119), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | GPT-6 Luna | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1391 | 1492 |
| LMArena Creative Writing | 1363 | 1468 |
| LMArena Multi-Turn | 1396 | 1464 |
Frequently asked questions
Is GPT-6 Luna better than MiMo-V2.6-Pro?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 50.3 on the Noometry Index.
Which is cheaper, GPT-6 Luna or MiMo-V2.6-Pro?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is GPT-6 Luna or MiMo-V2.6-Pro better for coding?
They score almost the same on coding (55.5 vs 55.5); test both on your own repository before choosing.
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-V2.6-Pro share?
19 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and MiMo-V2.6-Pro has 19.