Model comparison
GPT-5 Mini vs Trinity Large Thinking
GPT-5 Mini is the stronger model overall, scoring 41.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 1.8× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Arcee AISummary
- They share 20 benchmarks with published results for both. GPT-5 Mini scores higher in 8 categories and Trinity Large Thinking in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 37.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.9% for GPT-5 Mini and 6.9% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Trinity Large Thinking | |
|---|---|---|
| Provider | OpenAI | Arcee AI |
| Noometry Index | 41.8 | 38.6 |
| Released | 2025-08-07 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 80K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $2 | $0.80 |
| Results tracked | 60 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| SciCode | 39.2% | 36.1% |
| LMArena Coding | 1406 | 1381 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| LMArena WebDev | — | 1238 |
| SWE-bench Multilingual | 39.7% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Trinity Large Thinking: —
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1380 | 1350 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 54.3% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1378 | 1366 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 6.9% |
| LMArena Expert | 1379 | 1360 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Trinity Large Thinking: —
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1363 | 1325 |
| LMArena Chinese | 1385 | 1373 |
| LMArena French | 1386 | 1374 |
| LMArena German | 1366 | 1356 |
| LMArena Japanese | 1341 | 1311 |
| LMArena Korean | 1308 | 1306 |
| LMArena Russian | 1362 | 1337 |
| LMArena Spanish | 1355 | 1357 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1357 | 1334 |
| IFEval | 92.7% | — |
Long Context Too close to call
GPT-5 Mini: 41.9 (#132), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1355 | 1355 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GPT-5 Mini | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1373 | 1340 |
| LMArena Creative Writing | 1325 | 1320 |
| LMArena Multi-Turn | 1363 | 1342 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Trinity Large Thinking?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 1.8× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5 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; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or Trinity Large Thinking better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Mini and Trinity Large Thinking share?
20 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Trinity Large Thinking has 24.