Model comparison
Trinity Large Thinking vs Tulu 3 (Tülu 3) 70B
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Arcee AI
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Trinity Large Thinking scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 14.2.
Side by side
| Trinity Large Thinking | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Arcee AI | Allen Institute for AI (Ai2) |
| Noometry Index | 38.6 | 33.0 |
| Released | 2026-04-01 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 80K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.80 | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Trinity Large Thinking: 34.1 (#244), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1381 | 1235 |
| LMArena WebDev | 1238 | — |
| SciCode | 36.1% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Trinity Large Thinking: 16.9 (#298), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1350 | 1220 |
| NYT Connections (extended) | 16.5% | — |
| CritPt | 0.9% | — |
| Thematic Generalization | 41.6% | — |
| Surface Evolver Bench | 15.6% | — |
Math Trinity Large Thinking leads
Trinity Large Thinking: 37.6 (#149), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1366 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Trinity Large Thinking leads
Trinity Large Thinking: 40.9 (#113), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1360 | — |
Multilingual Trinity Large Thinking leads
Trinity Large Thinking: 46.2 (#160), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1325 | 1236 |
| LMArena Chinese | 1373 | 1249 |
| LMArena Russian | 1337 | 1246 |
| LMArena French | 1374 | — |
| LMArena German | 1356 | — |
| LMArena Japanese | 1311 | — |
| LMArena Korean | 1306 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Trinity Large Thinking leads
Trinity Large Thinking: 70.5 (#162), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1334 | 1233 |
Long Context Trinity Large Thinking leads
Trinity Large Thinking: 41.3 (#144), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1355 | 1224 |
Writing & Preference Trinity Large Thinking leads
Trinity Large Thinking: 53.8 (#158), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Trinity Large Thinking | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1340 | 1256 |
| LMArena Creative Writing | 1320 | 1231 |
| LMArena Multi-Turn | 1342 | 1252 |
Frequently asked questions
Is Trinity Large Thinking better than Tulu 3 (Tülu 3) 70B?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.0 on the Noometry Index.
Is Trinity Large Thinking or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 34.1 in the Noometry coding category.
How many benchmarks do Trinity Large Thinking and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Trinity Large Thinking has 24 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.