Model comparison
Amazon Nova Experimental Chat 10 20 vs Trinity Large Thinking
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 38.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Arcee AISummary
- They share 17 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 7 categories and Trinity Large Thinking in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Amazon Nova Experimental Chat 10 20 leads 28.4 to 16.9.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking | |
|---|---|---|
| Provider | Amazon | Arcee AI |
| Noometry Index | 42.1 | 38.6 |
| Released | — | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 17 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 41.6 (#123), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1412 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
Reasoning Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 28.4 (#106), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 39.0 (#119), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1425 | 1366 |
Knowledge Trinity Large Thinking leads
Amazon Nova Experimental Chat 10 20: 38.5 (#144), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1386 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 49.5 (#131), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1372 | 1325 |
| LMArena Chinese | 1404 | 1373 |
| LMArena French | 1425 | 1374 |
| LMArena German | 1391 | 1356 |
| LMArena Japanese | 1360 | 1311 |
| LMArena Korean | 1324 | 1306 |
| LMArena Russian | 1371 | 1337 |
| LMArena Spanish | 1382 | 1357 |
Instruction Following Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 72.1 (#141), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1365 | 1334 |
Long Context Too close to call
Amazon Nova Experimental Chat 10 20: 41.7 (#133), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1370 | 1355 |
Writing & Preference Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 56.6 (#136), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Amazon Nova Experimental Chat 10 20 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1394 | 1340 |
| LMArena Creative Writing | 1318 | 1320 |
| LMArena Multi-Turn | 1364 | 1342 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 20 better than Trinity Large Thinking?
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 38.6 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 20 or Trinity Large Thinking better for coding?
Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 34.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 20 and Trinity Large Thinking share?
17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Trinity Large Thinking has 24.