Model comparison
GPT-4.5 vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 36.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMaxSummary
- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and MiniMax-M2.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 37.7 to 32.4.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | MiniMax-M2.1 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 36.9 | 38.4 |
| Released | 2025-02-27 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 42 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 41.8 (#102), MiniMax-M2.1: 40.1 (#132)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1397 | 1421 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1384 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Too close to call
GPT-4.5: 27.6 (#92), MiniMax-M2.1: 27.7 (#91)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| Cybench | 17.5% | — |
Reasoning MiniMax-M2.1 leads
GPT-4.5: 14.1 (#320), MiniMax-M2.1: 15.8 (#301)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1410 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math MiniMax-M2.1 leads
GPT-4.5: 31.0 (#200), MiniMax-M2.1: 35.6 (#142)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1412 | 1396 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge MiniMax-M2.1 leads
GPT-4.5: 32.4 (#205), MiniMax-M2.1: 37.7 (#143)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1394 | 1432 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 11.8% |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), MiniMax-M2.1: —
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.7 (#78), MiniMax-M2.1: 50.2 (#123)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1413 | 1378 |
| LMArena Chinese | 1421 | 1430 |
| LMArena French | 1417 | 1405 |
| LMArena German | 1457 | 1380 |
| LMArena Japanese | 1416 | 1287 |
| LMArena Korean | 1392 | 1297 |
| LMArena Russian | 1419 | 1386 |
| LMArena Spanish | — | 1396 |
Instruction Following MiniMax-M2.1 leads
GPT-4.5: 72.8 (#129), MiniMax-M2.1: 74.0 (#108)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1399 |
| LiveBench Instruction Following | 72.3% | — |
Long Context MiniMax-M2.1 leads
GPT-4.5: 40.4 (#150), MiniMax-M2.1: 43.2 (#98)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1406 | 1416 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference MiniMax-M2.1 leads
GPT-4.5: 57.1 (#129), MiniMax-M2.1: 58.5 (#114)
| Benchmark | GPT-4.5 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1417 | 1392 |
| LMArena Creative Writing | 1394 | 1362 |
| LMArena Multi-Turn | 1444 | 1396 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 36.9 on the Noometry Index.
Is GPT-4.5 or MiniMax-M2.1 better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 40.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and MiniMax-M2.1 share?
16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiniMax-M2.1 has 22.