# GPT-5.5 Pro vs MiniMax-M2

> GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 36.9 on the Noometry Index. MiniMax-M2 costs 129× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-5-pro-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.6 to 18.6.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
- GPT-5.5 Pro accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 64.3 | 36.9 |
| Rank | 7 | 201 |
| Context | 1.05M | 205K |
| Input $/M | $30 | $0.30 |
| Output $/M | $180 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.5 Pro: —
- MiniMax-M2: 39.1 (#151)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| LMArena Coding | — | 1370 |

## Agentic & Tool Use

- GPT-5.5 Pro: —
- MiniMax-M2: 24.9 (#102)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-5.5 Pro: 73.6 (#7)
- MiniMax-M2: 18.6 (#256)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| SimpleBench | 76.9% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30.6% | — |
| Chess Puzzles | 64% | — |
| LMArena Hard Prompts | — | 1357 |
| DTBench | 96% | — |
| LMCA | 53.9% | — |
| Epoch Capabilities Index | 162.45 | — |

## Math

- GPT-5.5 Pro: 83.8 (#8)
- MiniMax-M2: 34.6 (#158)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87.7% | — |
| FrontierMath Tier 4 | 78% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| LMArena Math | — | 1350 |
| FrontierMath (Feb 2025 set) | 52.4% | — |
| FrontierMath Tier 4 (v1) | 39.6% | — |

## Knowledge

- GPT-5.5 Pro: 64.2 (#17)
- MiniMax-M2: 36.3 (#160)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| GPQA Diamond | 93.9% | — |
| LMArena Expert | — | 1336 |

## Multilingual

- GPT-5.5 Pro: —
- MiniMax-M2: 45.6 (#165)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1314 |
| LMArena Chinese | — | 1367 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- GPT-5.5 Pro: —
- MiniMax-M2: 70.4 (#160)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |

## Long Context

- GPT-5.5 Pro: —
- MiniMax-M2: 40.5 (#148)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1332 |

## Writing & Preference

- GPT-5.5 Pro: —
- MiniMax-M2: 53.3 (#157)

| Benchmark | GPT-5.5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1362 |

## FAQ

### Is GPT-5.5 Pro better than MiniMax-M2?

GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 36.9 on the Noometry Index. MiniMax-M2 costs 129× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.5 Pro or MiniMax-M2?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.5 Pro lists at $30 and $180.

### Which has the bigger context window?

GPT-5.5 Pro does, with 1.05M tokens against 205K.

### How many benchmarks do GPT-5.5 Pro and MiniMax-M2 share?

0 benchmarks have published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and MiniMax-M2 has 21.