# GPT-4.5 vs MiniMax-M2

> GPT-4.5 and MiniMax-M2 score almost the same on the Noometry Index (37.2 vs 37.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and MiniMax-M2 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4.5 leads 52.5 to 45.3.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 37.2 | 37.4 |
| Rank | 208 | 204 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 42.2 (#109)
- MiniMax-M2: 39.3 (#159)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1396 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1297 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.9 (#97)
- MiniMax-M2: 25.1 (#109)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Cybench | 17.5% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-4.5: 13.9 (#330)
- MiniMax-M2: 19.4 (#258)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1357 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| 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

- GPT-4.5: 32.6 (#211)
- MiniMax-M2: 37.3 (#160)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1412 | 1352 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.5 (#211)
- MiniMax-M2: 37.0 (#163)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1394 | 1337 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |

## Multimodal

- GPT-4.5: 37.6 (#71)
- MiniMax-M2: —

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.5 (#83)
- MiniMax-M2: 45.3 (#171)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1413 | 1313 |
| LMArena Chinese | 1421 | 1366 |
| LMArena French | 1418 | 1335 |
| LMArena German | 1457 | 1355 |
| LMArena Russian | 1419 | 1331 |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
| LMArena Spanish | — | 1326 |

## Instruction Following

- GPT-4.5: 72.6 (#134)
- MiniMax-M2: 70.2 (#166)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1328 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#155)
- MiniMax-M2: 40.5 (#153)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1406 | 1331 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 56.9 (#134)
- MiniMax-M2: 53.0 (#162)

| Benchmark | GPT-4.5 | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1417 | 1340 |
| LMArena Creative Writing | 1394 | 1286 |
| LMArena Multi-Turn | 1444 | 1361 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than MiniMax-M2?

GPT-4.5 and MiniMax-M2 score almost the same on the Noometry Index (37.2 vs 37.4), so choose on price, context window or the category you care about most.

### Is GPT-4.5 or MiniMax-M2 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 39.3 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and MiniMax-M2 share?

14 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and MiniMax-M2 has 21.