Model comparison
Amazon Nova Pro vs GPT-4.1 mini
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 categories and GPT-4.1 mini in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-4.1 mini leads 33.3 to 16.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 50.5% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-4.1 mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 33.6 |
| Released | 2024-12-03 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 33K |
| Input $ / M tokens | $0.80 | $0.40 |
| Output $ / M tokens | $3.20 | $1.60 |
| Results tracked | 38 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), GPT-4.1 mini: 30.6 (#293)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Coding | 1270 | 1367 |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| SciCode | — | 40.4% |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| LiveBench Coding | 38.1% | — |
| CadEval | — | 16% |
Agentic & Tool Use GPT-4.1 mini leads
Amazon Nova Pro: 16.7 (#147), GPT-4.1 mini: 33.3 (#55)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 50.5% |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), GPT-4.1 mini: 10.8 (#340)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1349 |
| Epoch Capabilities Index | 123.8 | 135.01 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 48.6% |
| ARC-AGI-1 | — | 3.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 21.1% |
| LiveBench | 43.5% | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), GPT-4.1 mini: 24.1 (#270)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| Omni-MATH | 24.2% | 49.1% |
| LMArena Math | 1252 | 1343 |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| OTIS Mock AIME 2024-2025 | — | 44.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
Knowledge GPT-4.1 mini leads
Amazon Nova Pro: 27.4 (#250), GPT-4.1 mini: 34.7 (#194)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| MMLU-Pro | 67.3% | 78.3% |
| GPQA (HELM) | 44.6% | 61.4% |
| LMArena Expert | 1211 | 1338 |
| GPQA Diamond | — | 65.8% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 12.7% |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 82% | — |
Multimodal GPT-4.1 mini leads
Amazon Nova Pro: 25.0 (#126), GPT-4.1 mini: 35.8 (#82)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 980 | 1181 |
Multilingual GPT-4.1 mini leads
Amazon Nova Pro: 39.7 (#223), GPT-4.1 mini: 45.7 (#166)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1234 | 1318 |
| LMArena Chinese | 1244 | 1329 |
| LMArena French | 1271 | 1358 |
| LMArena German | 1243 | 1351 |
| LMArena Japanese | 1200 | 1290 |
| LMArena Korean | 1203 | 1298 |
| LMArena Russian | 1240 | 1324 |
| LMArena Spanish | 1182 | 1319 |
Instruction Following GPT-4.1 mini leads
Amazon Nova Pro: 64.9 (#226), GPT-4.1 mini: 73.7 (#118)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| IFEval | 81.5% | 90.4% |
| LMArena Instruction Following | 1235 | 1333 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), GPT-4.1 mini: 31.8 (#275)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1255 | 1344 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-4.1 mini leads
Amazon Nova Pro: 43.9 (#226), GPT-4.1 mini: 48.6 (#199)
| Benchmark | Amazon Nova Pro | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1259 | 1340 |
| LMArena Creative Writing | 1212 | 1300 |
| WildBench | 77.7% | 83.8% |
| LMArena Multi-Turn | 1246 | 1354 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1147 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-4.1 mini?
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or GPT-4.1 mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or GPT-4.1 mini better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-4.1 mini share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-4.1 mini has 47.