Model comparison
Amazon Nova Pro vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and MiniMax-M2.5 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiniMax-M2.5 leads 30.4 to 16.7.
- 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.
Side by side
| Amazon Nova Pro | MiniMax-M2.5 | |
|---|---|---|
| Provider | Amazon | MiniMax |
| Noometry Index | 31.0 | 38.3 |
| Released | 2024-12-03 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | 300K | 205K |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.80 | $0.30 |
| Output $ / M tokens | $3.20 | $1.20 |
| Results tracked | 38 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Amazon Nova Pro: 35.1 (#229), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1270 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use MiniMax-M2.5 leads
Amazon Nova Pro: 16.7 (#147), MiniMax-M2.5: 30.4 (#77)
| 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 leads
Amazon Nova Pro: 20.0 (#243), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1372 |
| Epoch Capabilities Index | 123.8 | 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 leads
Amazon Nova Pro: 28.5 (#243), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1252 | 1378 |
| ProofBench | — | 4% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge MiniMax-M2.5 leads
Amazon Nova Pro: 27.4 (#250), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 9.1% |
| LMArena Expert | 1211 | 1379 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), MiniMax-M2.5: —
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual MiniMax-M2.5 leads
Amazon Nova Pro: 39.7 (#223), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1338 |
| LMArena Chinese | 1244 | 1393 |
| LMArena French | 1271 | 1362 |
| LMArena German | 1243 | 1362 |
| LMArena Japanese | 1200 | 1171 |
| LMArena Korean | 1203 | 1232 |
| LMArena Russian | 1240 | 1358 |
| LMArena Spanish | 1182 | 1354 |
Instruction Following MiniMax-M2.5 leads
Amazon Nova Pro: 64.9 (#226), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1353 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Amazon Nova Pro: 43.9 (#226), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Amazon Nova Pro | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1259 | 1359 |
| LMArena Creative Writing | 1212 | 1331 |
| LMArena Multi-Turn | 1246 | 1364 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1361 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.0 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: 48.1 versus 35.1 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.