# GPT-5.1 vs Llama 4 Scout

> GPT-5.1 is the stronger model overall, scoring 48.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 23× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-1-vs-llama-4-scout
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. GPT-5.1 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-5.1 leads 50.3 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.6% for GPT-5.1 and 7.8% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 48.8 | 27.4 |
| Rank | 47 | 323 |
| Context | 400K | 128K |
| Input $/M | $1.25 | $0.10 |
| Output $/M | $10 | $0.30 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.1: 46.9 (#59)
- Llama 4 Scout: 19.9 (#334)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | 9.1% |
| SciCode | 43.3% | 17% |
| LMArena Coding | 1454 | 1286 |
| SWE-bench Verified | 68% | — |
| LMArena WebDev | 1395 | — |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,192 | — |

## Agentic & Tool Use

- GPT-5.1: 32.5 (#55)
- Llama 4 Scout: 24.4 (#109)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |

## Reasoning

- GPT-5.1: 39.9 (#50)
- Llama 4 Scout: 9.2 (#339)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 17.6% | 0% |
| ARC-AGI-1 | 72.8% | 0.5% |
| CritPt | 4.9% | 0% |
| LMArena Hard Prompts | 1457 | 1266 |
| DTBench | 90.1% | 57.9% |
| LMCA | 43.9% | 12% |
| Epoch Capabilities Index | 149.66 | 129.64 |
| ForecastBench | 58.1 | 57.5 |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | — | 36.9% |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| LiveBench Data Analysis | 72.1% | — |
| LiveBench | 78.8% | — |

## Math

- GPT-5.1: 50.3 (#45)
- Llama 4 Scout: 18.4 (#280)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 7.8% |
| Omni-MATH | 46.4% | 37.3% |
| LMArena Math | 1446 | 1286 |
| FrontierMath (Feb 2025 set) | 31% | 0% |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 62.3% |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GPT-5.1: 50.5 (#65)
- Llama 4 Scout: 31.8 (#208)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 87.6% | 51.8% |
| MMLU-Pro | 57.9% | 74.2% |
| Vectara Hallucination Rate | 10.9% | 7.7% |
| GPQA (HELM) | 44.2% | 50.7% |
| LMArena Expert | 1470 | 1236 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |

## Multimodal

- GPT-5.1: 44.0 (#17)
- Llama 4 Scout: 31.6 (#98)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1250 | 1118 |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- GPT-5.1: 54.0 (#51)
- Llama 4 Scout: 41.3 (#207)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1431 | 1253 |
| LMArena Chinese | 1495 | 1256 |
| LMArena French | 1451 | 1283 |
| LMArena German | 1439 | 1274 |
| LMArena Japanese | 1453 | 1209 |
| LMArena Korean | 1401 | 1207 |
| LMArena Russian | 1435 | 1263 |
| LMArena Spanish | 1430 | 1277 |

## Instruction Following

- GPT-5.1: 84.0 (#1)
- Llama 4 Scout: 66.0 (#212)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| IFEval | 93.5% | 81.8% |
| LMArena Instruction Following | 1442 | 1248 |
| LiveBench Instruction Following | 93.3% | — |

## Long Context

- GPT-5.1: 47.6 (#14)
- Llama 4 Scout: 27.5 (#289)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1448 | 1265 |
| Fiction.LiveBench | — | 36% |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |

## Writing & Preference

- GPT-5.1: 64.7 (#53)
- Llama 4 Scout: 37.1 (#256)

| Benchmark | GPT-5.1 | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1443 | 1279 |
| LMArena Creative Writing | 1427 | 1249 |
| WildBench | 86.3% | 78% |
| LMArena Multi-Turn | 1449 | 1281 |
| EQ-Bench Creative Writing | — | 783 |
| LiveBench Language | 80.2% | — |

## FAQ

### Is GPT-5.1 better than Llama 4 Scout?

GPT-5.1 is the stronger model overall, scoring 48.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 23× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.1 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-5.1 lists at $1.25 and $10.

### Is GPT-5.1 or Llama 4 Scout better for coding?

GPT-5.1 scores higher on coding benchmarks: 46.9 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.1 does, with 400K tokens against 128K.

### How many benchmarks do GPT-5.1 and Llama 4 Scout share?

36 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Llama 4 Scout has 43.