Model comparison
Qwen3.8 Max vs Trinity Large Thinking
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 21 benchmarks with published results for both. Qwen3.8 Max 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 Qwen3.8 Max leads 54.4 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 88.3% for Qwen3.8 Max and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Qwen3.8 Max | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 56.8 | 38.6 |
| Released | 2026-08-02 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $0.80 |
| Results tracked | 39 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen3.8 Max: 53.5 (#29), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1674 | 1238 |
| SciCode | 53.2% | 36.1% |
| LMArena Coding | 1502 | 1381 |
| DeepSWE | 57.5% | — |
| FrontierSWE | 17.8% | — |
Agentic & Tool Use Not comparable
Qwen3.8 Max: 45.4 (#14), Trinity Large Thinking: —
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 63.3% | — |
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |
Reasoning Qwen3.8 Max leads
Qwen3.8 Max: 54.4 (#26), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 88.3% | 16.5% |
| CritPt | 20% | 0.9% |
| LMArena Hard Prompts | 1496 | 1350 |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 156.41 | — |
Math Qwen3.8 Max leads
Qwen3.8 Max: 73.2 (#20), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1499 | 1366 |
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
Knowledge Qwen3.8 Max leads
Qwen3.8 Max: 61.7 (#27), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1507 | 1360 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Qwen3.8 Max: 37.2 (#75), Trinity Large Thinking: —
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |
Multilingual Qwen3.8 Max leads
Qwen3.8 Max: 56.7 (#18), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1472 | 1325 |
| LMArena Chinese | 1538 | 1373 |
| LMArena French | 1503 | 1374 |
| LMArena German | 1483 | 1356 |
| LMArena Japanese | 1467 | 1311 |
| LMArena Korean | 1461 | 1306 |
| LMArena Russian | 1481 | 1337 |
| LMArena Spanish | 1492 | 1357 |
Instruction Following Qwen3.8 Max leads
Qwen3.8 Max: 77.6 (#17), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1479 | 1334 |
Long Context Qwen3.8 Max leads
Qwen3.8 Max: 45.6 (#31), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1489 | 1355 |
Writing & Preference Qwen3.8 Max leads
Qwen3.8 Max: 67.1 (#30), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3.8 Max | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1483 | 1340 |
| LMArena Creative Writing | 1479 | 1320 |
| LMArena Multi-Turn | 1489 | 1342 |
Frequently asked questions
Is Qwen3.8 Max better than Trinity Large Thinking?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.7× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.8 Max 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; Qwen3.8 Max lists at $2 and $6.
Is Qwen3.8 Max or Trinity Large Thinking better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Qwen3.8 Max and Trinity Large Thinking share?
21 benchmarks have published results for both models. Qwen3.8 Max has 39 scored results on Noometry and Trinity Large Thinking has 24.