# GPT-5 Pro vs MiniMax-M2

> GPT-5 Pro is the stronger model overall, scoring 46.4 to 37.4 on the Noometry Index. MiniMax-M2 costs 79× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-pro-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5 Pro scores higher in 4 categories and MiniMax-M2 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Pro leads 56.7 to 37.0.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 76.8% for GPT-5 Pro and 57.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 46.4 | 37.4 |
| Rank | 64 | 204 |
| Context | 400K | 205K |
| Input $/M | $15 | $0.30 |
| Output $/M | $120 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Pro: 44.0 (#80)
- MiniMax-M2: 39.3 (#159)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1370 |
| AlgoTune | 1.31 | — |

## Agentic & Tool Use

- GPT-5 Pro: —
- MiniMax-M2: 25.1 (#109)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-5 Pro: 38.9 (#62)
- MiniMax-M2: 19.4 (#258)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 76.8% | 57.8% |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 70.2% | — |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1357 |
| Epoch Capabilities Index | 150.28 | — |

## Math

- GPT-5 Pro: 48.5 (#63)
- MiniMax-M2: 37.3 (#160)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| LMArena Math | — | 1352 |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- GPT-5 Pro: 56.7 (#42)
- MiniMax-M2: 37.0 (#163)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| LMArena Expert | — | 1337 |

## Multilingual

- GPT-5 Pro: —
- MiniMax-M2: 45.3 (#171)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- GPT-5 Pro: —
- MiniMax-M2: 70.2 (#166)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |

## Long Context

- GPT-5 Pro: —
- MiniMax-M2: 40.5 (#153)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |

## Writing & Preference

- GPT-5 Pro: —
- MiniMax-M2: 53.0 (#162)

| Benchmark | GPT-5 Pro | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1286 |
| LMArena Multi-Turn | — | 1361 |

## FAQ

### Is GPT-5 Pro better than MiniMax-M2?

GPT-5 Pro is the stronger model overall, scoring 46.4 to 37.4 on the Noometry Index. MiniMax-M2 costs 79× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-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 Pro lists at $15 and $120.

### Is GPT-5 Pro or MiniMax-M2 better for coding?

GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 39.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Pro does, with 400K tokens against 205K.

### How many benchmarks do GPT-5 Pro and MiniMax-M2 share?

1 benchmark has published results for both models. GPT-5 Pro has 12 scored results on Noometry and MiniMax-M2 has 21.