Model comparison
GPT-4.1 mini vs Llama 4 Maverick
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.3× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
MetaSummary
- They share 42 benchmarks with published results for both. GPT-4.1 mini scores higher in 9 categories and Llama 4 Maverick in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 mini leads 48.6 to 38.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 20.6% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 mini | Llama 4 Maverick | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 33.6 | 30.9 |
| Released | 2025-04-14 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.40 | $0.19 |
| Output $ / M tokens | $1.60 | $0.65 |
| Results tracked | 47 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 mini leads
GPT-4.1 mini: 30.6 (#293), Llama 4 Maverick: 26.6 (#324)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 21% |
| Aider Polyglot | 32.4% | 15.6% |
| SciCode | 40.4% | 33.1% |
| WeirdML | 37.6% | 24.5% |
| BigCodeBench Instruct | 48.9% | 49.7% |
| LMArena Coding | 1367 | 1302 |
| BigCodeBench Complete | — | 61.4% |
| CadEval | 16% | — |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.3 (#55), Llama 4 Maverick: 28.2 (#91)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 37.3% |
Reasoning Too close to call
GPT-4.1 mini: 10.8 (#340), Llama 4 Maverick: 10.1 (#342)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 48.6% | 55.9% |
| ARC-AGI-1 | 3.5% | 4.4% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1349 | 1281 |
| DTBench | 68.8% | 61.9% |
| LMCA | 21.1% | 15.9% |
| Epoch Capabilities Index | 135.01 | 132.2 |
| SimpleBench | — | 27.7% |
| NYT Connections (extended) | — | 8% |
| Chess Puzzles | 7% | — |
| EnigmaEval | — | 0.6% |
| Mystery Game Puzzles | 7% | — |
| ForecastBench | — | 57.5 |
Math Llama 4 Maverick leads
GPT-4.1 mini: 24.1 (#270), Llama 4 Maverick: 26.0 (#262)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 20.6% |
| Omni-MATH | 49.1% | 42.2% |
| LMArena Math | 1343 | 1299 |
| MATH Level 5 | 87.3% | 73% |
| FrontierMath (Feb 2025 set) | 4.5% | 0.7% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
Knowledge GPT-4.1 mini leads
GPT-4.1 mini: 34.7 (#194), Llama 4 Maverick: 33.4 (#204)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 65.8% | 67% |
| MMLU-Pro | 78.3% | 81% |
| GPQA (HELM) | 61.4% | 65% |
| LMArena Expert | 1338 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 12.7% | — |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
Multimodal GPT-4.1 mini leads
GPT-4.1 mini: 35.8 (#82), Llama 4 Maverick: 31.6 (#105)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1181 | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual GPT-4.1 mini leads
GPT-4.1 mini: 45.7 (#166), Llama 4 Maverick: 42.2 (#195)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1318 | 1269 |
| LMArena Chinese | 1329 | 1277 |
| LMArena French | 1358 | 1259 |
| LMArena German | 1351 | 1291 |
| LMArena Japanese | 1290 | 1207 |
| LMArena Korean | 1298 | 1203 |
| LMArena Russian | 1324 | 1286 |
| LMArena Spanish | 1319 | 1293 |
Instruction Following GPT-4.1 mini leads
GPT-4.1 mini: 73.7 (#118), Llama 4 Maverick: 71.7 (#146)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| IFEval | 90.4% | 90.8% |
| LMArena Instruction Following | 1333 | 1267 |
Long Context Too close to call
GPT-4.1 mini: 31.8 (#275), Llama 4 Maverick: 31.4 (#279)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | 44.4% | 46.2% |
| LMArena Longer Query | 1344 | 1280 |
Writing & Preference GPT-4.1 mini leads
GPT-4.1 mini: 48.6 (#199), Llama 4 Maverick: 38.8 (#252)
| Benchmark | GPT-4.1 mini | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1340 | 1287 |
| LMArena Creative Writing | 1300 | 1267 |
| EQ-Bench Creative Writing | 1147 | 860 |
| WildBench | 83.8% | 80% |
| LMArena Multi-Turn | 1354 | 1289 |
| Short-Story Creative Writing | — | 62% |
Frequently asked questions
Is GPT-4.1 mini better than Llama 4 Maverick?
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 30.9 on the Noometry Index. Llama 4 Maverick costs 2.3× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or Llama 4 Maverick?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.
Is GPT-4.1 mini or Llama 4 Maverick better for coding?
GPT-4.1 mini scores higher on coding benchmarks: 30.6 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4.1 mini and Llama 4 Maverick share?
42 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Llama 4 Maverick has 54.