Model comparison
Llama 3.2 1B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 5.5× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Meta
Arcee AISummary
- They share 13 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 7.2.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 60K.
Side by side
| Llama 3.2 1B | Trinity Large Thinking | |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 20.1 | 38.6 |
| Released | 2024-09-24 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 60K | 262K |
| Max output | 54K | 80K |
| Input $ / M tokens | $0.027 | $0.25 |
| Output $ / M tokens | $0.20 | $0.80 |
| Results tracked | 22 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Llama 3.2 1B: 21.1 (#338), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1070 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 8.2% | — |
| BigCodeBench Complete | 11.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 1B: 14.6 (#150), Trinity Large Thinking: —
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |
Reasoning Too close to call
Llama 3.2 1B: 16.2 (#308), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 101.99 | — |
Math Trinity Large Thinking leads
Llama 3.2 1B: 10.4 (#313), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1086 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
Knowledge Trinity Large Thinking leads
Llama 3.2 1B: 7.2 (#312), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1007 | 1360 |
| GPQA Diamond | 23.9% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Trinity Large Thinking leads
Llama 3.2 1B: 23.8 (#292), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 973 | 1325 |
| LMArena Chinese | 959 | 1373 |
| LMArena German | 1014 | 1356 |
| LMArena Russian | 941 | 1337 |
| LMArena French | — | 1374 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Spanish | — | 1357 |
Instruction Following Trinity Large Thinking leads
Llama 3.2 1B: 52.4 (#290), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1031 | 1334 |
Long Context Trinity Large Thinking leads
Llama 3.2 1B: 31.9 (#274), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1050 | 1355 |
Writing & Preference Trinity Large Thinking leads
Llama 3.2 1B: 21.3 (#310), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Llama 3.2 1B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1055 | 1340 |
| LMArena Creative Writing | 1033 | 1320 |
| LMArena Multi-Turn | 1030 | 1342 |
| EQ-Bench Creative Writing | 200 | — |
Frequently asked questions
Is Llama 3.2 1B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 20.1 on the Noometry Index. Llama 3.2 1B costs 5.5× 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 3.2 1B or Trinity Large Thinking?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Llama 3.2 1B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 21.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 60K.
How many benchmarks do Llama 3.2 1B and Trinity Large Thinking share?
13 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Trinity Large Thinking has 24.