Model comparison
GLM-4.7 vs Trinity Large Thinking
GLM-4.7 is the stronger model overall, scoring 42.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.6× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Arcee AISummary
- They share 21 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.7 leads 44.0 to 34.1.
- The biggest single-benchmark swing is SciCode: 45.1% for GLM-4.7 and 36.1% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- Trinity Large Thinking accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.7 | Trinity Large Thinking | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Arcee AI |
| Noometry Index | 42.0 | 38.6 |
| Released | 2025-12-22 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $0.60 | $0.25 |
| Output $ / M tokens | $2.20 | $0.80 |
| Results tracked | 36 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), Trinity Large Thinking: 34.1 (#244)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1435 | 1238 |
| SciCode | 45.1% | 36.1% |
| LMArena Coding | 1454 | 1381 |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Trinity Large Thinking: —
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 24.3 (#164), Trinity Large Thinking: 16.9 (#298)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| CritPt | 1.7% | 0.9% |
| LMArena Hard Prompts | 1443 | 1350 |
| SimpleBench | 47.7% | — |
| NYT Connections (extended) | — | 16.5% |
| Chess Puzzles | 6% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 143.51 | — |
Math Too close to call
GLM-4.7: 38.6 (#135), Trinity Large Thinking: 37.6 (#149)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1423 | 1366 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), Trinity Large Thinking: 40.9 (#113)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 11.7% | 6.9% |
| LMArena Expert | 1424 | 1360 |
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Trinity Large Thinking: 46.2 (#160)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1417 | 1325 |
| LMArena Chinese | 1495 | 1373 |
| LMArena French | 1432 | 1374 |
| LMArena German | 1424 | 1356 |
| LMArena Japanese | 1439 | 1311 |
| LMArena Korean | 1399 | 1306 |
| LMArena Russian | 1423 | 1337 |
| LMArena Spanish | 1434 | 1357 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Trinity Large Thinking: 70.5 (#162)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1411 | 1334 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Trinity Large Thinking: 41.3 (#144)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1432 | 1355 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Trinity Large Thinking: 53.8 (#158)
| Benchmark | GLM-4.7 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1435 | 1340 |
| LMArena Creative Writing | 1401 | 1320 |
| LMArena Multi-Turn | 1446 | 1342 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Trinity Large Thinking?
GLM-4.7 is the stronger model overall, scoring 42.0 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.6× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 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-4.7 lists at $0.60 and $2.20.
Is GLM-4.7 or Trinity Large Thinking better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 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-4.7 and Trinity Large Thinking share?
21 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Trinity Large Thinking has 24.