Model comparison
Qwen3.5 122B-A10B vs Trinity Large Thinking
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.8× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 23 benchmarks with published results for both. Qwen3.5 122B-A10B scores higher in 7 categories and Trinity Large Thinking in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 122B-A10B leads 27.2 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 51.7% for Qwen3.5 122B-A10B and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
Side by side
| Qwen3.5 122B-A10B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 42.1 | 38.6 |
| Released | 2026-02-23 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $0.40 | $0.25 |
| Output $ / M tokens | $3.20 | $0.80 |
| Results tracked | 27 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 39.1 (#162), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1360 | 1238 |
| SciCode | 35.6% | 36.1% |
| LMArena Coding | 1436 | 1381 |
Reasoning Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 27.2 (#123), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 51.7% | 16.5% |
| CritPt | 0.9% | 0.9% |
| Thematic Generalization | 51.2% | 41.6% |
| LMArena Hard Prompts | 1421 | 1350 |
| Mystery Game Puzzles | 17% | — |
| DTBench | 84.3% | — |
| LMCA | 32.2% | — |
| Surface Evolver Bench | — | 15.6% |
Math Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 39.1 (#112), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1432 | 1366 |
Knowledge Trinity Large Thinking leads
Qwen3.5 122B-A10B: 38.8 (#142), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 11.2% | 6.9% |
| LMArena Expert | 1432 | 1360 |
Multimodal Not comparable
Qwen3.5 122B-A10B: 39.6 (#57), Trinity Large Thinking: —
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 51.6 (#107), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1400 | 1325 |
| LMArena Chinese | 1462 | 1373 |
| LMArena French | 1442 | 1374 |
| LMArena German | 1426 | 1356 |
| LMArena Japanese | 1367 | 1311 |
| LMArena Korean | 1352 | 1306 |
| LMArena Russian | 1400 | 1337 |
| LMArena Spanish | 1424 | 1357 |
Instruction Following Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 73.8 (#115), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1399 | 1334 |
Long Context Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 43.0 (#109), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1410 | 1355 |
Writing & Preference Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 60.0 (#105), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3.5 122B-A10B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1417 | 1340 |
| LMArena Creative Writing | 1368 | 1320 |
| LMArena Multi-Turn | 1416 | 1342 |
Frequently asked questions
Is Qwen3.5 122B-A10B better than Trinity Large Thinking?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.8× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5 122B-A10B 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; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Qwen3.5 122B-A10B or Trinity Large Thinking better for coding?
Qwen3.5 122B-A10B scores higher on coding benchmarks: 39.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.5 122B-A10B and Trinity Large Thinking share?
23 benchmarks have published results for both models. Qwen3.5 122B-A10B has 27 scored results on Noometry and Trinity Large Thinking has 24.