Model comparison
GPT-5 Mini vs Llama 4 Scout
GPT-5 Mini is the stronger model overall, scoring 41.8 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.6× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
MetaSummary
- They share 41 benchmarks with published results for both. GPT-5 Mini scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.7% for GPT-5 Mini and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 41.8 | 27.7 |
| Released | 2025-08-07 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.25 | $0.10 |
| Output $ / M tokens | $2 | $0.30 |
| Results tracked | 60 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 59.8% | 9.1% |
| SciCode | 39.2% | 17% |
| LMArena Coding | 1406 | 1286 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Multilingual | 39.7% | — |
| WeirdML | 52.7% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.5% | 28.1% |
| Terminal-Bench | 34.8% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 4.4% | 0% |
| Kagi LLM Benchmark | 70.3% | 36.9% |
| ARC-AGI-1 | 54.3% | 0.5% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1380 | 1266 |
| DTBench | 80.5% | 57.9% |
| LMCA | 34.2% | 12% |
| Epoch Capabilities Index | 145.52 | 129.64 |
| ForecastBench | 61 | 57.5 |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 7.8% |
| Omni-MATH | 72.2% | 37.3% |
| LMArena Math | 1378 | 1287 |
| MATH Level 5 | 97.8% | 62.3% |
| FrontierMath (Feb 2025 set) | 27.2% | 0% |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 75% | 51.8% |
| MMLU-Pro | 83.5% | 74.2% |
| Vectara Hallucination Rate | 12.9% | 7.7% |
| GPQA (HELM) | 75.6% | 50.7% |
| LMArena Expert | 1379 | 1235 |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| Confabulations | 13.3% | — |
Multimodal GPT-5 Mini leads
GPT-5 Mini: 35.6 (#85), Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1202 | 1118 |
| VPCT | 40.2% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1363 | 1252 |
| LMArena Chinese | 1385 | 1255 |
| LMArena French | 1386 | 1282 |
| LMArena German | 1366 | 1272 |
| LMArena Japanese | 1341 | 1206 |
| LMArena Korean | 1308 | 1207 |
| LMArena Russian | 1362 | 1263 |
| LMArena Spanish | 1355 | 1278 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| IFEval | 92.7% | 81.8% |
| LMArena Instruction Following | 1357 | 1248 |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#132), Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | 69.4% | 36% |
| LMArena Longer Query | 1355 | 1265 |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-5 Mini | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1373 | 1279 |
| LMArena Creative Writing | 1325 | 1249 |
| EQ-Bench Creative Writing | 1313 | 783 |
| WildBench | 85.5% | 78% |
| LMArena Multi-Turn | 1363 | 1280 |
| Short-Story Creative Writing | 83.1% | — |
Frequently asked questions
Is GPT-5 Mini better than Llama 4 Scout?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.6× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5 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-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or Llama 4 Scout better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 128K.
How many benchmarks do GPT-5 Mini and Llama 4 Scout share?
41 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Llama 4 Scout has 43.