Model comparison
o1 vs Trinity Large Thinking
o1 is the stronger model overall, scoring 40.6 to 38.1 on the Noometry Index. Trinity Large Thinking costs 68× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Arcee AISummary
- They share 17 benchmarks with published results for both. o1 scores higher in 7 categories and Trinity Large Thinking in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where o1 leads 45.7 to 33.8.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $15 / $60 for o1.
- Trinity Large Thinking accepts more context: 262K tokens versus 200K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| o1 | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 40.6 | 38.1 |
| Released | 2024-09-12 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 80K |
| Input $ / M tokens | $15 | $0.25 |
| Output $ / M tokens | $60 | $0.80 |
| Results tracked | 52 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
o1: 45.7 (#64), Trinity Large Thinking: 33.8 (#238)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1367 | 1381 |
| Aider Polyglot | 61.7% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 47.6% | — |
| LiveBench Coding | 69.7% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |
Agentic & Tool Use Not comparable
o1: 24.3 (#111), Trinity Large Thinking: —
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |
Reasoning o1 leads
o1: 27.5 (#103), Trinity Large Thinking: 16.3 (#298)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1350 |
| SimpleBench | 41.7% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 30.7% | — |
| CritPt | — | 0.9% |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 91.6% | — |
| DTBench | 74.7% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | 22.3% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 141.92 | — |
| LiveBench | 75.7% | — |
Math Too close to call
o1: 34.9 (#150), Trinity Large Thinking: 34.9 (#149)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1388 | 1366 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LiveBench Math | 80.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |
Knowledge o1 leads
o1: 41.5 (#101), Trinity Large Thinking: 40.3 (#107)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1362 | 1359 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
o1: 33.6 (#87), Trinity Large Thinking: —
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |
Multilingual o1 leads
o1: 48.8 (#137), Trinity Large Thinking: 46.4 (#155)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1359 | 1325 |
| LMArena Chinese | 1394 | 1372 |
| LMArena French | 1343 | 1374 |
| LMArena German | 1337 | 1356 |
| LMArena Japanese | 1346 | 1312 |
| LMArena Korean | 1396 | 1304 |
| LMArena Russian | 1356 | 1338 |
| LMArena Spanish | 1345 | 1356 |
Instruction Following o1 leads
o1: 75.0 (#82), Trinity Large Thinking: 70.7 (#157)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1368 | 1334 |
| LiveBench Instruction Following | 81.5% | — |
Long Context o1 leads
o1: 50.3 (#9), Trinity Large Thinking: 41.2 (#139)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1378 | 1355 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference o1 leads
o1: 55.8 (#139), Trinity Large Thinking: 54.0 (#152)
| Benchmark | o1 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1366 | 1340 |
| LMArena Creative Writing | 1347 | 1321 |
| LMArena Multi-Turn | 1368 | 1342 |
| Short-Story Creative Writing | 70.2% | — |
| LiveBench Language | 65.4% | — |
Frequently asked questions
Is o1 better than Trinity Large Thinking?
o1 is the stronger model overall, scoring 40.6 to 38.1 on the Noometry Index. Trinity Large Thinking costs 68× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, o1 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; o1 lists at $15 and $60.
Is o1 or Trinity Large Thinking better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 200K.
How many benchmarks do o1 and Trinity Large Thinking share?
17 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Trinity Large Thinking has 24.