Model comparison
Llama 4 Maverick vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Arcee AISummary
- They share 21 benchmarks with published results for both. Llama 4 Maverick scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 38.8.
- The biggest single-benchmark swing is NYT Connections (extended): 8% for Llama 4 Maverick and 16.5% for Trinity Large Thinking.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 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 Maverick | Trinity Large Thinking | |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 30.9 | 38.6 |
| Released | 2025-04-05 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 80K |
| Input $ / M tokens | $0.19 | $0.25 |
| Output $ / M tokens | $0.65 | $0.80 |
| Results tracked | 54 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Llama 4 Maverick: 26.6 (#324), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| SciCode | 33.1% | 36.1% |
| LMArena Coding | 1302 | 1381 |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| LMArena WebDev | — | 1238 |
| WeirdML | 24.5% | — |
| BigCodeBench Instruct | 49.7% | — |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 28.2 (#91), Trinity Large Thinking: —
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Trinity Large Thinking leads
Llama 4 Maverick: 10.1 (#342), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 8% | 16.5% |
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1281 | 1350 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| ARC-AGI-1 | 4.4% | — |
| EnigmaEval | 0.6% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Trinity Large Thinking leads
Llama 4 Maverick: 26.0 (#262), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1299 | 1366 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Trinity Large Thinking leads
Llama 4 Maverick: 33.4 (#204), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 8.2% | 6.9% |
| LMArena Expert | 1259 | 1360 |
| GPQA Diamond | 67% | — |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Trinity Large Thinking: —
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Trinity Large Thinking leads
Llama 4 Maverick: 42.2 (#195), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1269 | 1325 |
| LMArena Chinese | 1277 | 1373 |
| LMArena French | 1259 | 1374 |
| LMArena German | 1291 | 1356 |
| LMArena Japanese | 1207 | 1311 |
| LMArena Korean | 1203 | 1306 |
| LMArena Russian | 1286 | 1337 |
| LMArena Spanish | 1293 | 1357 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1267 | 1334 |
| IFEval | 90.8% | — |
Long Context Trinity Large Thinking leads
Llama 4 Maverick: 31.4 (#279), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1280 | 1355 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Trinity Large Thinking leads
Llama 4 Maverick: 38.8 (#252), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Llama 4 Maverick | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1287 | 1340 |
| LMArena Creative Writing | 1267 | 1320 |
| LMArena Multi-Turn | 1289 | 1342 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.9 on the Noometry Index.
Which is cheaper, Llama 4 Maverick or Trinity Large Thinking?
Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Llama 4 Maverick or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 26.6 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 Maverick and Trinity Large Thinking share?
21 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Trinity Large Thinking has 24.