Model comparison
GPT-6 Sol vs MiniMax-M2.5
GPT-6 Sol is the stronger model overall, scoring 49.2 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 7.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 17.6.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 16.8% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | MiniMax-M2.5 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 49.2 | 38.1 |
| Released | 2026-09-22 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 22 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 59.6 (#11), MiniMax-M2.5: 47.9 (#53)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1692 | 1386 |
| LMArena Coding | 1453 | 1380 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 33.5 (#49), MiniMax-M2.5: 30.2 (#70)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| GDP.pdf | 28% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), MiniMax-M2.5: 17.6 (#281)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 16.8% |
| LMArena Hard Prompts | 1420 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| ARC-AGI-1 | — | 63.7% |
| EBR-Bench | 53.3% | — |
| Epoch Capabilities Index | — | 146.68 |
Math GPT-6 Sol leads
GPT-6 Sol: 35.8 (#135), MiniMax-M2.5: 25.8 (#242)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1404 | 1378 |
| ProofBench | — | 4% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 43.0 (#87), MiniMax-M2.5: 38.6 (#132)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 6.5% | 9.1% |
| LMArena Expert | 1449 | 1378 |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#9), MiniMax-M2.5: —
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 51.0 (#113), MiniMax-M2.5: 47.3 (#147)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1389 | 1338 |
| LMArena Chinese | 1416 | 1392 |
| LMArena Russian | 1407 | 1359 |
| LMArena Spanish | 1377 | 1354 |
| LMArena French | — | 1363 |
| LMArena German | — | 1361 |
| LMArena Japanese | — | 1169 |
| LMArena Korean | — | 1232 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.4 (#97), MiniMax-M2.5: 71.7 (#143)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1353 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.2 (#100), MiniMax-M2.5: 37.4 (#211)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1415 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 72.3 (#15), MiniMax-M2.5: 54.1 (#149)
| Benchmark | GPT-6 Sol | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1396 | 1359 |
| LMArena Creative Writing | 1392 | 1331 |
| EQ-Bench Creative Writing | 2125 | 1361 |
| LMArena Multi-Turn | 1405 | 1364 |
Frequently asked questions
Is GPT-6 Sol better than MiniMax-M2.5?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 7.6× 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 MiniMax-M2.5?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or MiniMax-M2.5 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 47.9 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 205K.
How many benchmarks do GPT-6 Sol and MiniMax-M2.5 share?
17 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and MiniMax-M2.5 has 33.