Model comparison
GPT-6.1 Sol vs Llama 4 Scout
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 27× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GPT-6.1 Sol 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-6.1 Sol leads 93.7 to 19.6.
- The biggest single-benchmark swing is ARC-AGI-1: 98.5% for GPT-6.1 Sol and 0.5% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Llama 4 Scout | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 65.6 | 27.7 |
| Released | 2026-09-29 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $10 | $0.30 |
| Results tracked | 34 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Llama 4 Scout: 20.2 (#339)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| SciCode | 55.8% | 17% |
| LMArena Coding | 1487 | 1286 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1755 | — |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Llama 4 Scout: 24.6 (#119)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| APEX-Agents | 60% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Llama 4 Scout: 9.1 (#345)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 94.2% | 0% |
| ARC-AGI-1 | 98.5% | 0.5% |
| CritPt | 31.7% | 0% |
| LMArena Hard Prompts | 1466 | 1266 |
| Epoch Capabilities Index | 166.09 | 129.64 |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 95.5% | — |
| Chess Puzzles | 61% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Llama 4 Scout: 19.6 (#286)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 7.8% |
| LMArena Math | 1464 | 1287 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| ProofBench | 99% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Llama 4 Scout: 31.9 (#217)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 95.4% | 51.8% |
| LMArena Expert | 1502 | 1235 |
| SimpleQA Verified | 73.9% | — |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), Llama 4 Scout: 32.2 (#102)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1288 | 1118 |
| Furniture Assembly | 80% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), Llama 4 Scout: 41.0 (#212)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1438 | 1252 |
| LMArena Chinese | 1477 | 1255 |
| LMArena Russian | 1455 | 1263 |
| LMArena French | — | 1282 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Spanish | — | 1278 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Llama 4 Scout: 65.8 (#217)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1468 | 1248 |
| IFEval | — | 81.8% |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), Llama 4 Scout: 27.5 (#294)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1465 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), Llama 4 Scout: 37.0 (#261)
| Benchmark | GPT-6.1 Sol | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1447 | 1279 |
| LMArena Creative Writing | 1432 | 1249 |
| LMArena Multi-Turn | 1449 | 1280 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
Frequently asked questions
Is GPT-6.1 Sol better than Llama 4 Scout?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 27× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol 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-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Llama 4 Scout better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 128K.
How many benchmarks do GPT-6.1 Sol and Llama 4 Scout share?
20 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Llama 4 Scout has 43.