Model comparison
GPT-5.4 mini vs Llama 4 Scout
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 27.7 on the Noometry Index. Llama 4 Scout costs 11× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GPT-5.4 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 writing & preference, where GPT-5.4 mini leads 64.0 to 37.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 mini | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.0 | 27.7 |
| Released | 2026-03-17 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.75 | $0.10 |
| Output $ / M tokens | $4.50 | $0.30 |
| Results tracked | 46 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| SciCode | 49.9% | 17% |
| LMArena Coding | 1438 | 1286 |
| FrontierCode | 27% | — |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1397 | — |
| WeirdML | 60.3% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use GPT-5.4 mini leads
GPT-5.4 mini: 29.9 (#81), Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 18.9% | 0% |
| Kagi LLM Benchmark | 37.9% | 36.9% |
| ARC-AGI-1 | 63.7% | 0.5% |
| CritPt | 10% | 0% |
| LMArena Hard Prompts | 1424 | 1266 |
| DTBench | 80% | 57.9% |
| LMCA | 40.8% | 12% |
| Epoch Capabilities Index | 148.84 | 129.64 |
| ForecastBench | 57 | 57.5 |
| NYT Connections (extended) | 61.8% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 7.8% |
| LMArena Math | 1419 | 1287 |
| FrontierMath (Feb 2025 set) | 28.3% | 0% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 86.9% | 51.8% |
| Vectara Hallucination Rate | 5.5% | 7.7% |
| LMArena Expert | 1435 | 1235 |
| SimpleQA Verified | 29.4% | — |
| MMLU-Pro | — | 74.2% |
| GPQA (HELM) | — | 50.7% |
Multimodal GPT-5.4 mini leads
GPT-5.4 mini: 39.7 (#56), Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1245 | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 51.9 (#96), Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1405 | 1252 |
| LMArena Chinese | 1446 | 1255 |
| LMArena French | 1440 | 1282 |
| LMArena German | 1409 | 1272 |
| LMArena Japanese | 1374 | 1206 |
| LMArena Korean | 1368 | 1207 |
| LMArena Russian | 1417 | 1263 |
| LMArena Spanish | 1405 | 1278 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1405 | 1248 |
| IFEval | — | 81.8% |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 43.0 (#112), Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1407 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-5.4 mini | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1412 | 1279 |
| LMArena Creative Writing | 1370 | 1249 |
| EQ-Bench Creative Writing | 1665 | 783 |
| LMArena Multi-Turn | 1429 | 1280 |
| WildBench | — | 78% |
Frequently asked questions
Is GPT-5.4 mini better than Llama 4 Scout?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 27.7 on the Noometry Index. Llama 4 Scout costs 11× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 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-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Llama 4 Scout better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 128K.
How many benchmarks do GPT-5.4 mini and Llama 4 Scout share?
32 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Llama 4 Scout has 43.