Model comparison
GPT-4o mini vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Arcee AISummary
- They share 17 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 10.4.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 25.5 | 38.6 |
| Released | 2024-07-18 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 16K | 80K |
| Input $ / M tokens | $0.15 | $0.25 |
| Output $ / M tokens | $0.60 | $0.80 |
| Results tracked | 60 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
GPT-4o mini: 22.0 (#335), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1290 | 1381 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Trinity Large Thinking: —
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Trinity Large Thinking leads
GPT-4o mini: 8.7 (#347), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1350 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Trinity Large Thinking leads
GPT-4o mini: 10.4 (#314), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1267 | 1366 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Trinity Large Thinking leads
GPT-4o mini: 17.7 (#284), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1235 | 1360 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| Vectara Hallucination Rate | — | 6.9% |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Trinity Large Thinking: —
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Trinity Large Thinking leads
GPT-4o mini: 42.0 (#199), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1266 | 1325 |
| LMArena Chinese | 1265 | 1373 |
| LMArena French | 1297 | 1374 |
| LMArena German | 1272 | 1356 |
| LMArena Japanese | 1216 | 1311 |
| LMArena Korean | 1195 | 1306 |
| LMArena Russian | 1275 | 1337 |
| LMArena Spanish | 1276 | 1357 |
Instruction Following Trinity Large Thinking leads
GPT-4o mini: 61.9 (#239), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1258 | 1334 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Trinity Large Thinking leads
GPT-4o mini: 39.1 (#186), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1289 | 1355 |
Writing & Preference Trinity Large Thinking leads
GPT-4o mini: 39.5 (#248), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GPT-4o mini | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1286 | 1340 |
| LMArena Creative Writing | 1268 | 1320 |
| LMArena Multi-Turn | 1285 | 1342 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 25.5 on the Noometry Index.
Which is cheaper, GPT-4o mini or Trinity Large Thinking?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is GPT-4o mini or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 128K.
How many benchmarks do GPT-4o mini and Trinity Large Thinking share?
17 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Trinity Large Thinking has 24.