Model comparison
GLM-5.2 vs Trinity Large Thinking
GLM-5.2 is the stronger model overall, scoring 51.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 5.5× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Arcee AISummary
- They share 22 benchmarks with published results for both. GLM-5.2 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 GLM-5.2 leads 42.3 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 74.3% for GLM-5.2 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 262K.
Side by side
| GLM-5.2 | Trinity Large Thinking | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Arcee AI |
| Noometry Index | 51.1 | 38.6 |
| Released | 2026-06-13 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $1.40 | $0.25 |
| Output $ / M tokens | $4.40 | $0.80 |
| Results tracked | 51 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1603 | 1238 |
| SciCode | 50.5% | 36.1% |
| LMArena Coding | 1485 | 1381 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), Trinity Large Thinking: —
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 74.3% | 16.5% |
| CritPt | 20.9% | 0.9% |
| LMArena Hard Prompts | 1480 | 1350 |
| Surface Evolver Bench | 55.6% | 15.6% |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| Chess Puzzles | 21% | — |
| Thematic Generalization | — | 41.6% |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Epoch Capabilities Index | 151.78 | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1482 | 1366 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1486 | 1360 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1459 | 1325 |
| LMArena Chinese | 1519 | 1373 |
| LMArena French | 1479 | 1374 |
| LMArena German | 1468 | 1356 |
| LMArena Japanese | 1451 | 1311 |
| LMArena Korean | 1445 | 1306 |
| LMArena Russian | 1466 | 1337 |
| LMArena Spanish | 1477 | 1357 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1465 | 1334 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1479 | 1355 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GLM-5.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1470 | 1340 |
| LMArena Creative Writing | 1462 | 1320 |
| LMArena Multi-Turn | 1469 | 1342 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Trinity Large Thinking?
GLM-5.2 is the stronger model overall, scoring 51.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 5.5× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 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; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Trinity Large Thinking better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Trinity Large Thinking share?
22 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Trinity Large Thinking has 24.