Model comparison
GPT-6 Sol vs MiMo-V2.5-Pro
GPT-6 Sol is the stronger model overall, scoring 61.8 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 7.4× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GPT-6 Sol scores higher in 5 categories and MiMo-V2.5-Pro in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 26.8.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 22% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol 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 Sol | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 61.8 | 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 | $2 | $0.43 |
| Output $ / M tokens | $10 | $0.87 |
| Results tracked | 45 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1688 | 1479 |
| SciCode | 57.6% | 50.2% |
| LMArena Coding | 1447 | 1503 |
| ALE-Bench | 2,462 | 899.8 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), MiMo-V2.5-Pro: —
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 90.1% | 34.4% |
| CritPt | 30.9% | 4% |
| LMArena Hard Prompts | 1418 | 1488 |
| DTBench | 97.3% | 84.5% |
| LMCA | 59.1% | 29.5% |
| ARC-AGI-2 | 89.6% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 83% | 22% |
| LMArena Math | 1402 | 1481 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1439 | 1503 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), MiMo-V2.5-Pro: —
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual MiMo-V2.5-Pro leads
GPT-6 Sol: 50.5 (#118), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1385 | 1449 |
| LMArena Chinese | 1405 | 1507 |
| LMArena French | 1410 | 1488 |
| LMArena German | 1390 | 1458 |
| LMArena Japanese | 1385 | 1412 |
| LMArena Korean | 1341 | 1437 |
| LMArena Russian | 1401 | 1450 |
| LMArena Spanish | 1384 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
GPT-6 Sol: 74.5 (#94), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1412 | 1477 |
Long Context MiMo-V2.5-Pro leads
GPT-6 Sol: 43.1 (#108), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1411 | 1483 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | GPT-6 Sol | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1395 | 1465 |
| LMArena Creative Writing | 1378 | 1440 |
| EQ-Bench Creative Writing | 2125 | 1493 |
| LMArena Multi-Turn | 1412 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is GPT-6 Sol better than MiMo-V2.5-Pro?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 7.4× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or MiMo-V2.5-Pro better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 47.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-6 Sol and MiMo-V2.5-Pro share?
26 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and MiMo-V2.5-Pro has 27.