Model comparison
Gemma 2 27B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
Arcee AISummary
- They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 10.7.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Trinity Large Thinking accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 2 27B | Trinity Large Thinking | |
|---|---|---|
| Provider | Arcee AI | |
| Noometry Index | 29.4 | 38.6 |
| Released | 2024-06-24 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 2K | 80K |
| Input $ / M tokens | $0.65 | $0.25 |
| Output $ / M tokens | $0.65 | $0.80 |
| Results tracked | 34 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 27B: 34.1 (#246), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1211 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Trinity Large Thinking leads
Gemma 2 27B: 15.3 (#315), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math Trinity Large Thinking leads
Gemma 2 27B: 10.7 (#311), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1212 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Trinity Large Thinking leads
Gemma 2 27B: 19.0 (#280), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1172 | 1360 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 6.9% |
| MMLU | 75.7% | — |
Multilingual Trinity Large Thinking leads
Gemma 2 27B: 38.6 (#226), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1217 | 1325 |
| LMArena Chinese | 1221 | 1373 |
| LMArena French | 1247 | 1374 |
| LMArena German | 1209 | 1356 |
| LMArena Japanese | 1175 | 1311 |
| LMArena Korean | 1174 | 1306 |
| LMArena Russian | 1234 | 1337 |
| LMArena Spanish | 1228 | 1357 |
Instruction Following Trinity Large Thinking leads
Gemma 2 27B: 60.5 (#249), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1206 | 1334 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Trinity Large Thinking leads
Gemma 2 27B: 37.3 (#218), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1231 | 1355 |
Writing & Preference Trinity Large Thinking leads
Gemma 2 27B: 44.2 (#225), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Gemma 2 27B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1231 | 1340 |
| LMArena Creative Writing | 1241 | 1320 |
| LMArena Multi-Turn | 1224 | 1342 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B 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; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Trinity Large Thinking better for coding?
They score almost the same on coding (34.1 vs 34.1); test both on your own repository before choosing.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 8K.
How many benchmarks do Gemma 2 27B and Trinity Large Thinking share?
17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Trinity Large Thinking has 24.