Model comparison
Llama 4 Scout vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.6× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Meta
Arcee AISummary
- They share 20 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 54.0 to 37.1.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 36.1% for Trinity Large Thinking.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Trinity Large Thinking | |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 27.4 | 38.1 |
| Released | 2025-04-05 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 80K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $0.80 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Llama 4 Scout: 19.9 (#334), Trinity Large Thinking: 33.8 (#238)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| SciCode | 17% | 36.1% |
| LMArena Coding | 1286 | 1381 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1238 |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.4 (#109), Trinity Large Thinking: —
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Trinity Large Thinking leads
Llama 4 Scout: 9.2 (#339), Trinity Large Thinking: 16.3 (#298)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1266 | 1350 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 0.5% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Trinity Large Thinking leads
Llama 4 Scout: 18.4 (#280), Trinity Large Thinking: 34.9 (#149)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1286 | 1366 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Trinity Large Thinking leads
Llama 4 Scout: 31.8 (#208), Trinity Large Thinking: 40.3 (#107)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 7.7% | 6.9% |
| LMArena Expert | 1236 | 1359 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Trinity Large Thinking: —
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Trinity Large Thinking leads
Llama 4 Scout: 41.3 (#207), Trinity Large Thinking: 46.4 (#155)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1253 | 1325 |
| LMArena Chinese | 1256 | 1372 |
| LMArena French | 1283 | 1374 |
| LMArena German | 1274 | 1356 |
| LMArena Japanese | 1209 | 1312 |
| LMArena Korean | 1207 | 1304 |
| LMArena Russian | 1263 | 1338 |
| LMArena Spanish | 1277 | 1356 |
Instruction Following Trinity Large Thinking leads
Llama 4 Scout: 66.0 (#212), Trinity Large Thinking: 70.7 (#157)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1248 | 1334 |
| IFEval | 81.8% | — |
Long Context Trinity Large Thinking leads
Llama 4 Scout: 27.5 (#289), Trinity Large Thinking: 41.2 (#139)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1265 | 1355 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Trinity Large Thinking leads
Llama 4 Scout: 37.1 (#256), Trinity Large Thinking: 54.0 (#152)
| Benchmark | Llama 4 Scout | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1279 | 1340 |
| LMArena Creative Writing | 1249 | 1321 |
| LMArena Multi-Turn | 1281 | 1342 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.6× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Trinity Large Thinking?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Llama 4 Scout or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Trinity Large Thinking share?
20 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Trinity Large Thinking has 24.