Model comparison
GPT-6 Luna vs MiMo-V2.5-Pro
GPT-6 Luna is the stronger model overall, scoring 53.3 to 45.2 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-6 Luna scores higher in 4 categories and MiMo-V2.5-Pro in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 40.0.
- The biggest single-benchmark swing is ProofBench: 64% for GPT-6 Luna and 22% for MiMo-V2.5-Pro.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 53.3 | 45.2 |
| Released | 2026-09-22 | 2026-04-22 |
| 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 | 27 |
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-V2.5-Pro: 47.4 (#60)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1581 | 1479 |
| SciCode | 54.6% | 50.2% |
| LMArena Coding | 1439 | 1503 |
| ALE-Bench | 1,577 | 899.8 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
Agentic & Tool Use Not comparable
GPT-6 Luna: 33.3 (#54), MiMo-V2.5-Pro: —
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 44.3% | — |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 68.7% | 34.4% |
| CritPt | 19.4% | 4% |
| LMArena Hard Prompts | 1411 | 1488 |
| DTBench | 90.1% | 84.5% |
| LMCA | 44.5% | 29.5% |
| ARC-AGI-2 | 59.3% | — |
| ARC-AGI-1 | 86.7% | — |
| Chess Puzzles | 31% | — |
| Mystery Game Puzzles | 7% | — |
| Epoch Capabilities Index | 156.28 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 64% | 22% |
| LMArena Math | 1416 | 1481 |
| 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-V2.5-Pro: 42.2 (#98)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1444 | 1503 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
Multimodal Not comparable
GPT-6 Luna: 42.4 (#30), MiMo-V2.5-Pro: —
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1217 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual MiMo-V2.5-Pro leads
GPT-6 Luna: 50.5 (#117), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1386 | 1449 |
| LMArena Chinese | 1433 | 1507 |
| LMArena French | 1420 | 1488 |
| LMArena German | 1369 | 1458 |
| LMArena Japanese | 1369 | 1412 |
| LMArena Korean | 1360 | 1437 |
| LMArena Russian | 1394 | 1450 |
| LMArena Spanish | 1393 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
GPT-6 Luna: 74.3 (#99), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1409 | 1477 |
Long Context MiMo-V2.5-Pro leads
GPT-6 Luna: 43.0 (#111), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1409 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
GPT-6 Luna: 58.3 (#119), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1391 | 1465 |
| LMArena Creative Writing | 1363 | 1440 |
| LMArena Multi-Turn | 1396 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-6 Luna better than MiMo-V2.5-Pro?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 45.2 on the Noometry Index.
Which is cheaper, GPT-6 Luna or MiMo-V2.5-Pro?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is GPT-6 Luna or MiMo-V2.5-Pro better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 47.4 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-V2.5-Pro share?
25 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and MiMo-V2.5-Pro has 27.