Model comparison
GPT-4o mini vs Llama 4 Scout
Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
MetaSummary
- They share 33 benchmarks with published results for both. GPT-4o mini scores higher in 5 categories and Llama 4 Scout in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 17.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 57.4% for GPT-4o mini and 43.1% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.15 / $0.60 for GPT-4o mini.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 25.5 | 27.7 |
| Released | 2024-07-18 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $0.15 | $0.10 |
| Output $ / M tokens | $0.60 | $0.30 |
| Results tracked | 60 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4o mini leads
GPT-4o mini: 22.0 (#335), Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1290 | 1286 |
| BigCodeBench Complete | 57.4% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| Aider Polyglot | 3.6% | — |
| SciCode | — | 17% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use GPT-4o mini leads
GPT-4o mini: 27.5 (#101), Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
| BALROG | 17.4% | — |
Reasoning Too close to call
GPT-4o mini: 8.7 (#347), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 28.8% | 36.9% |
| LMArena Hard Prompts | 1267 | 1266 |
| DTBench | 54.4% | 57.9% |
| LMCA | 10.4% | 12% |
| Epoch Capabilities Index | 126.56 | 129.64 |
| SimpleBench | 10.7% | — |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| ForecastBench | — | 57.5 |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Llama 4 Scout leads
GPT-4o mini: 10.4 (#314), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 7.8% |
| Omni-MATH | 28% | 37.3% |
| LMArena Math | 1267 | 1287 |
| MATH Level 5 | 52.6% | 62.3% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | 36.3% | — |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | 91.3% | — |
Knowledge Llama 4 Scout leads
GPT-4o mini: 17.7 (#284), Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 37.7% | 51.8% |
| MMLU-Pro | 60.3% | 74.2% |
| GPQA (HELM) | 36.8% | 50.7% |
| LMArena Expert | 1235 | 1235 |
| SimpleQA Verified | 8.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 7.7% |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Llama 4 Scout leads
GPT-4o mini: 25.9 (#122), Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1066 | 1118 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Too close to call
GPT-4o mini: 42.0 (#199), Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1266 | 1252 |
| LMArena Chinese | 1265 | 1255 |
| LMArena French | 1297 | 1282 |
| LMArena German | 1272 | 1272 |
| LMArena Japanese | 1216 | 1206 |
| LMArena Korean | 1195 | 1207 |
| LMArena Russian | 1275 | 1263 |
| LMArena Spanish | 1276 | 1278 |
Instruction Following Llama 4 Scout leads
GPT-4o mini: 61.9 (#239), Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| IFEval | 78.2% | 81.8% |
| LMArena Instruction Following | 1258 | 1248 |
| LiveBench Instruction Following | 56.8% | — |
Long Context GPT-4o mini leads
GPT-4o mini: 39.1 (#186), Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1289 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference GPT-4o mini leads
GPT-4o mini: 39.5 (#248), Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-4o mini | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1286 | 1279 |
| LMArena Creative Writing | 1268 | 1249 |
| EQ-Bench Creative Writing | 873 | 783 |
| WildBench | 79.1% | 78% |
| LMArena Multi-Turn | 1285 | 1280 |
| Short-Story Creative Writing | 67.2% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Llama 4 Scout?
Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.5 on the Noometry Index.
Which is cheaper, GPT-4o mini or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; GPT-4o mini lists at $0.15 and $0.60.
Is GPT-4o mini or Llama 4 Scout better for coding?
GPT-4o mini scores higher on coding benchmarks: 22.0 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4o mini and Llama 4 Scout share?
33 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Llama 4 Scout has 43.