# Amazon Nova Pro vs MiniMax-M2.5

> MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and MiniMax-M2.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiniMax-M2.5 leads 30.2 to 16.6.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 30.5 | 38.1 |
| Rank | 278 | 181 |
| Context | 300K | 205K |
| Input $/M | $0.80 | $0.30 |
| Output $/M | $3.20 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 34.6 (#224)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1270 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1386 |
| SWE-bench Multilingual | — | 68.3% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 618.17 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.6 (#139)
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Amazon Nova Pro: 19.2 (#240)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1372 |
| Epoch Capabilities Index | 123.75 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 26.4 (#240)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1252 | 1378 |
| ProofBench | — | 4% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.1 (#246)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 9.1% |
| LMArena Expert | 1211 | 1378 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 24.5 (#121)
- MiniMax-M2.5: —

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.9 (#218)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1338 |
| LMArena Chinese | 1244 | 1392 |
| LMArena French | 1270 | 1363 |
| LMArena German | 1243 | 1361 |
| LMArena Japanese | 1200 | 1169 |
| LMArena Korean | 1203 | 1232 |
| LMArena Russian | 1240 | 1359 |
| LMArena Spanish | 1182 | 1354 |

## Instruction Following

- Amazon Nova Pro: 65.1 (#221)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1353 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#199)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Amazon Nova Pro: 44.1 (#221)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1259 | 1359 |
| LMArena Creative Writing | 1212 | 1331 |
| LMArena Multi-Turn | 1245 | 1364 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1361 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 30.5 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro 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; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 34.6 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 205K.

### How many benchmarks do Amazon Nova Pro and MiniMax-M2.5 share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and MiniMax-M2.5 has 33.