Model comparison
Amazon Nova Pro vs MiMo-V2.5
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and MiMo-V2.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 44.1.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 300K.
- MiMo-V2.5 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | MiMo-V2.5 | |
|---|---|---|
| Provider | Amazon | Xiaomi |
| Noometry Index | 30.5 | 43.0 |
| Released | 2024-12-03 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | 300K | 1.05M |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.80 | $0.14 |
| Output $ / M tokens | $3.20 | $0.28 |
| Results tracked | 38 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Amazon Nova Pro: 34.6 (#224), MiMo-V2.5: 43.6 (#75)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1270 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 513.95 |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.6 (#139), MiMo-V2.5: —
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning MiMo-V2.5 leads
Amazon Nova Pro: 19.2 (#240), MiMo-V2.5: 27.8 (#98)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1450 |
| CritPt | — | 3.7% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.75 | — |
| LiveBench | 43.5% | — |
Math MiMo-V2.5 leads
Amazon Nova Pro: 26.4 (#240), MiMo-V2.5: 35.4 (#145)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1252 | 1436 |
| ProofBench | — | 16% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge MiMo-V2.5 leads
Amazon Nova Pro: 27.1 (#246), MiMo-V2.5: 40.2 (#109)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1211 | 1459 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal MiMo-V2.5 leads
Amazon Nova Pro: 24.5 (#121), MiMo-V2.5: 39.0 (#53)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 980 | 1245 |
Multilingual MiMo-V2.5 leads
Amazon Nova Pro: 39.9 (#218), MiMo-V2.5: 52.0 (#96)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1234 | 1404 |
| LMArena Chinese | 1244 | 1467 |
| LMArena French | 1270 | 1447 |
| LMArena German | 1243 | 1421 |
| LMArena Japanese | 1200 | 1304 |
| LMArena Korean | 1203 | 1363 |
| LMArena Russian | 1240 | 1395 |
| LMArena Spanish | 1182 | 1412 |
Instruction Following MiMo-V2.5 leads
Amazon Nova Pro: 65.1 (#221), MiMo-V2.5: 75.7 (#55)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1433 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context MiMo-V2.5 leads
Amazon Nova Pro: 38.1 (#199), MiMo-V2.5: 44.1 (#69)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1255 | 1444 |
Writing & Preference MiMo-V2.5 leads
Amazon Nova Pro: 44.1 (#221), MiMo-V2.5: 61.8 (#82)
| Benchmark | Amazon Nova Pro | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1259 | 1427 |
| LMArena Creative Writing | 1212 | 1392 |
| LMArena Multi-Turn | 1245 | 1445 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than MiMo-V2.5?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 30.5 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 34.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and MiMo-V2.5 share?
18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and MiMo-V2.5 has 23.