Model comparison
GLM-5 vs Trinity Large Thinking
GLM-5 is the stronger model overall, scoring 46.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 4.0× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Arcee AISummary
- They share 20 benchmarks with published results for both. GLM-5 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5 leads 49.0 to 34.1.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Trinity Large Thinking accepts more context: 262K tokens versus 205K.
Side by side
| GLM-5 | Trinity Large Thinking | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Arcee AI |
| Noometry Index | 46.1 | 38.6 |
| Released | 2026-02-11 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $1 | $0.25 |
| Output $ / M tokens | $3.20 | $0.80 |
| Results tracked | 45 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1434 | 1238 |
| LMArena Coding | 1461 | 1381 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 36.1% |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Trinity Large Thinking: —
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 74.8% | 16.5% |
| LMArena Hard Prompts | 1452 | 1350 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 0.9% |
| Chess Puzzles | 10% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1440 | 1366 |
| MathArena Final-Answer Competitions | 65.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 10.1% | 6.9% |
| LMArena Expert | 1454 | 1360 |
| GPQA Diamond | 87.8% | — |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1430 | 1325 |
| LMArena Chinese | 1511 | 1373 |
| LMArena French | 1455 | 1374 |
| LMArena German | 1445 | 1356 |
| LMArena Japanese | 1416 | 1311 |
| LMArena Korean | 1423 | 1306 |
| LMArena Russian | 1436 | 1337 |
| LMArena Spanish | 1454 | 1357 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1428 | 1334 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1446 | 1355 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GLM-5 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1446 | 1340 |
| LMArena Creative Writing | 1439 | 1320 |
| LMArena Multi-Turn | 1456 | 1342 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Trinity Large Thinking?
GLM-5 is the stronger model overall, scoring 46.1 to 38.6 on the Noometry Index. Trinity Large Thinking costs 4.0× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-5 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 lists at $1 and $3.20.
Is GLM-5 or Trinity Large Thinking better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 205K.
How many benchmarks do GLM-5 and Trinity Large Thinking share?
20 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Trinity Large Thinking has 24.