Model comparison
Qwen3.5 397B-A17B vs Trinity Large Thinking
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 3.5× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 20 benchmarks with published results for both. Qwen3.5 397B-A17B scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 58.9% for Qwen3.5 397B-A17B and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
Side by side
| Qwen3.5 397B-A17B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 46.0 | 38.6 |
| Released | 2026-02-01 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $0.60 | $0.25 |
| Output $ / M tokens | $3.60 | $0.80 |
| Results tracked | 36 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 42.0 (#114), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1400 | 1238 |
| LMArena Coding | 1465 | 1381 |
| SciCode | — | 36.1% |
Agentic & Tool Use Not comparable
Qwen3.5 397B-A17B: 33.3 (#53), Trinity Large Thinking: —
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 24.9% | — |
| τ²-bench Airline | 81.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 84.4% | — |
| τ²-bench Telecom | 97.8% | — |
Reasoning Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 34.5 (#70), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 58.9% | 16.5% |
| Thematic Generalization | 65.1% | 41.6% |
| LMArena Hard Prompts | 1448 | 1350 |
| Kagi LLM Benchmark | 73.7% | — |
| CritPt | — | 0.9% |
| Chess Puzzles | 13% | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 87.5% | — |
| LMCA | 37.9% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 146.65 | — |
Math Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 46.1 (#73), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1454 | 1366 |
| FrontierMath (Tiers 1-3) | 31.2% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
Knowledge Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 53.3 (#58), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1462 | 1360 |
| GPQA Diamond | 86.4% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Qwen3.5 397B-A17B: 40.7 (#44), Trinity Large Thinking: —
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1263 | — |
Multilingual Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 53.7 (#59), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1430 | 1325 |
| LMArena Chinese | 1500 | 1373 |
| LMArena French | 1461 | 1374 |
| LMArena German | 1447 | 1356 |
| LMArena Japanese | 1426 | 1311 |
| LMArena Korean | 1384 | 1306 |
| LMArena Russian | 1429 | 1337 |
| LMArena Spanish | 1441 | 1357 |
Instruction Following Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 75.0 (#77), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1424 | 1334 |
Long Context Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 44.1 (#74), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1442 | 1355 |
Writing & Preference Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 62.3 (#79), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3.5 397B-A17B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1438 | 1340 |
| LMArena Creative Writing | 1401 | 1320 |
| LMArena Multi-Turn | 1446 | 1342 |
| EQ-Bench Creative Writing | 1478 | — |
Frequently asked questions
Is Qwen3.5 397B-A17B better than Trinity Large Thinking?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 3.5× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5 397B-A17B 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 397B-A17B lists at $0.60 and $3.60.
Is Qwen3.5 397B-A17B or Trinity Large Thinking better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.5 397B-A17B and Trinity Large Thinking share?
20 benchmarks have published results for both models. Qwen3.5 397B-A17B has 36 scored results on Noometry and Trinity Large Thinking has 24.