Model comparison
Qwen3-30B-A3B vs Trinity Large Thinking
Qwen3-30B-A3B and Trinity Large Thinking score almost the same on the Noometry Index (38.9 vs 38.6), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 19 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 6 categories and Trinity Large Thinking in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Trinity Large Thinking leads 41.3 to 31.0.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 41K.
Side by side
| Qwen3-30B-A3B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 38.9 | 38.6 |
| Released | 2025-04-28 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 41K | 262K |
| Max output | 16K | 80K |
| Input $ / M tokens | $0.12 | $0.25 |
| Output $ / M tokens | $0.50 | $0.80 |
| Results tracked | 32 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Qwen3-30B-A3B: 37.5 (#194), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| SciCode | 33.3% | 36.1% |
| LMArena Coding | 1416 | 1381 |
| LMArena WebDev | — | 1238 |
| WeirdML | 29.8% | — |
Agentic & Tool Use Not comparable
Qwen3-30B-A3B: 29.8 (#82), Trinity Large Thinking: —
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |
Reasoning Qwen3-30B-A3B leads
Qwen3-30B-A3B: 22.2 (#204), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| CritPt | 0.3% | 0.9% |
| LMArena Hard Prompts | 1398 | 1350 |
| Kagi LLM Benchmark | 54.9% | — |
| NYT Connections (extended) | — | 16.5% |
| Chess Puzzles | 8% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 69.3% | — |
| LMCA | 22.4% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 139.63 | — |
Math Too close to call
Qwen3-30B-A3B: 37.4 (#157), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1394 | 1366 |
| MathArena Final-Answer Competitions | 47.8% | — |
| OTIS Mock AIME 2024-2025 | 70.3% | — |
Knowledge Too close to call
Qwen3-30B-A3B: 41.8 (#105), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1396 | 1360 |
| GPQA Diamond | 70.1% | — |
| Confabulations | 12.3% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Qwen3-30B-A3B leads
Qwen3-30B-A3B: 49.5 (#132), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1372 | 1325 |
| LMArena Chinese | 1433 | 1373 |
| LMArena French | 1418 | 1374 |
| LMArena German | 1380 | 1356 |
| LMArena Japanese | 1337 | 1311 |
| LMArena Korean | 1331 | 1306 |
| LMArena Russian | 1370 | 1337 |
| LMArena Spanish | 1404 | 1357 |
Instruction Following Qwen3-30B-A3B leads
Qwen3-30B-A3B: 72.0 (#142), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1363 | 1334 |
Long Context Trinity Large Thinking leads
Qwen3-30B-A3B: 31.0 (#283), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1379 | 1355 |
| Fiction.LiveBench | 40.6% | — |
Writing & Preference Qwen3-30B-A3B leads
Qwen3-30B-A3B: 55.6 (#143), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3-30B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1384 | 1340 |
| LMArena Creative Writing | 1317 | 1320 |
| LMArena Multi-Turn | 1378 | 1342 |
| Short-Story Creative Writing | 75.3% | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Trinity Large Thinking?
Qwen3-30B-A3B and Trinity Large Thinking score almost the same on the Noometry Index (38.9 vs 38.6), so choose on price, context window or the category you care about most.
Which is cheaper, Qwen3-30B-A3B or Trinity Large Thinking?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Qwen3-30B-A3B or Trinity Large Thinking better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 41K.
How many benchmarks do Qwen3-30B-A3B and Trinity Large Thinking share?
19 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Trinity Large Thinking has 24.