Model comparison
GPT-4.1 vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Arcee AISummary
- They share 18 benchmarks with published results for both. GPT-4.1 scores higher in 4 categories and Trinity Large Thinking in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 22.3.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 35.9 | 38.6 |
| Released | 2025-04-14 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 80K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $8 | $0.80 |
| Results tracked | 52 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1391 | 1381 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Trinity Large Thinking: —
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Trinity Large Thinking leads
GPT-4.1: 11.7 (#339), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1350 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0.9% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Trinity Large Thinking leads
GPT-4.1: 22.3 (#280), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1370 | 1366 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Trinity Large Thinking leads
GPT-4.1: 37.1 (#160), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 5.6% | 6.9% |
| LMArena Expert | 1364 | 1360 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Trinity Large Thinking: —
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1370 | 1325 |
| LMArena Chinese | 1382 | 1373 |
| LMArena French | 1382 | 1374 |
| LMArena German | 1381 | 1356 |
| LMArena Japanese | 1319 | 1311 |
| LMArena Korean | 1339 | 1306 |
| LMArena Russian | 1377 | 1337 |
| LMArena Spanish | 1376 | 1357 |
Instruction Following Too close to call
GPT-4.1: 71.3 (#153), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1367 | 1334 |
| IFEval | 83.8% | — |
Long Context Trinity Large Thinking leads
GPT-4.1: 40.0 (#163), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1385 | 1355 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GPT-4.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1383 | 1340 |
| LMArena Creative Writing | 1363 | 1320 |
| LMArena Multi-Turn | 1398 | 1342 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Trinity Large Thinking better for coding?
They score almost the same on coding (34.4 vs 34.1); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 and Trinity Large Thinking share?
18 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Trinity Large Thinking has 24.