Model comparison
GPT-6 Sol vs MiMo-V2.6-Pro
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.3 on the Noometry Index. MiMo-V2.6-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 . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GPT-6 Sol scores higher in 6 categories and MiMo-V2.6-Pro in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 54.5.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 70% for MiMo-V2.6-Pro.
- MiMo-V2.6-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-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Noometry Index | 61.8 | 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 | $2 | $0.43 |
| Output $ / M tokens | $10 | $0.87 |
| Results tracked | 45 | 19 |
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-V2.6-Pro: 55.5 (#23)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1688 | 1629 |
| SciCode | 57.6% | 60.9% |
| LMArena Coding | 1447 | 1534 |
| ALE-Bench | 2,462 | 1,158 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
Agentic & Tool Use Too close to call
GPT-6 Sol: 37.2 (#36), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 54.3% | 59.5% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 30.9% | 26.6% |
| LMArena Hard Prompts | 1418 | 1512 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 83% | 70% |
| LMArena Math | 1402 | 1494 |
| 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-V2.6-Pro: 43.5 (#92)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1439 | 1543 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1245 | 1264 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual MiMo-V2.6-Pro leads
GPT-6 Sol: 50.5 (#118), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1385 | 1474 |
| LMArena Chinese | 1405 | 1529 |
| LMArena Russian | 1401 | 1480 |
| LMArena French | 1410 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1385 | — |
| LMArena Korean | 1341 | — |
| LMArena Spanish | 1384 | — |
Instruction Following MiMo-V2.6-Pro leads
GPT-6 Sol: 74.5 (#94), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1412 | 1493 |
Long Context MiMo-V2.6-Pro leads
GPT-6 Sol: 43.1 (#108), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1411 | 1501 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | GPT-6 Sol | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1395 | 1492 |
| LMArena Creative Writing | 1378 | 1468 |
| LMArena Multi-Turn | 1412 | 1464 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than MiMo-V2.6-Pro?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.3 on the Noometry Index. MiMo-V2.6-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-V2.6-Pro?
MiMo-V2.6-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-V2.6-Pro better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 55.5 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-V2.6-Pro share?
19 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and MiMo-V2.6-Pro has 19.