Model comparison
o3-mini vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 36.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Arcee AISummary
- They share 19 benchmarks with published results for both. o3-mini scores higher in 2 categories and Trinity Large Thinking in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 28.1.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- 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
| o3-mini | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 36.7 | 38.6 |
| Released | 2024-12-20 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 80K |
| Input $ / M tokens | $1.10 | $0.25 |
| Output $ / M tokens | $4.40 | $0.80 |
| Results tracked | 51 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Trinity Large Thinking: 34.1 (#244)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| SciCode | 39.8% | 36.1% |
| LMArena Coding | 1378 | 1381 |
| Aider Polyglot | 60.4% | — |
| LMArena WebDev | — | 1238 |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
o3-mini: 29.6 (#84), Trinity Large Thinking: —
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning Too close to call
o3-mini: 16.3 (#305), Trinity Large Thinking: 16.9 (#298)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| CritPt | 0.3% | 0.9% |
| LMArena Hard Prompts | 1366 | 1350 |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 34.5% | — |
| Chess Puzzles | 17% | — |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 89.6% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LiveBench Data Analysis | 70.6% | — |
| LMCA | 19% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 140.34 | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Trinity Large Thinking leads
o3-mini: 28.1 (#244), Trinity Large Thinking: 37.6 (#149)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1396 | 1366 |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 76.9% | — |
| LiveBench Math | 77.3% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Trinity Large Thinking leads
o3-mini: 38.3 (#146), Trinity Large Thinking: 40.9 (#113)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1364 | 1360 |
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Too close to call
o3-mini: 45.7 (#164), Trinity Large Thinking: 46.2 (#160)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1319 | 1325 |
| LMArena Chinese | 1379 | 1373 |
| LMArena French | 1334 | 1374 |
| LMArena German | 1303 | 1356 |
| LMArena Japanese | 1286 | 1311 |
| LMArena Korean | 1314 | 1306 |
| LMArena Russian | 1304 | 1337 |
| LMArena Spanish | 1321 | 1357 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Trinity Large Thinking: 70.5 (#162)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1337 | 1334 |
| LiveBench Instruction Following | 84.4% | — |
Long Context Trinity Large Thinking leads
o3-mini: 33.8 (#256), Trinity Large Thinking: 41.3 (#144)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1343 | 1355 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Trinity Large Thinking leads
o3-mini: 50.3 (#182), Trinity Large Thinking: 53.8 (#158)
| Benchmark | o3-mini | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1337 | 1340 |
| LMArena Creative Writing | 1286 | 1320 |
| LMArena Multi-Turn | 1320 | 1342 |
| Short-Story Creative Writing | 61.7% | — |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini 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; o3-mini lists at $1.10 and $4.40.
Is o3-mini or Trinity Large Thinking better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 200K.
How many benchmarks do o3-mini and Trinity Large Thinking share?
19 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Trinity Large Thinking has 24.