Model comparison
GLM-4.5-Air vs Tulu 3 (Tülu 3) 70B
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 36.2 to 14.2.
Side by side
| GLM-4.5-Air | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 38.9 | 33.0 |
| Released | 2025-07-20 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
GLM-4.5-Air: 33.3 (#259), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1397 | 1235 |
| GSO | 2.9% | — |
Reasoning Too close to call
GLM-4.5-Air: 24.1 (#166), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1220 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1396 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| Omni-MATH | 39.1% | — |
| MATH Level 5 | — | 42.7% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1370 | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1366 | 1236 |
| LMArena Chinese | 1426 | 1249 |
| LMArena Russian | 1373 | 1246 |
| LMArena French | 1399 | — |
| LMArena German | 1377 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1386 | — |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1354 | 1233 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1366 | 1224 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | GLM-4.5-Air | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1384 | 1256 |
| LMArena Creative Writing | 1343 | 1231 |
| LMArena Multi-Turn | 1371 | 1252 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Tulu 3 (Tülu 3) 70B?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.0 on the Noometry Index.
Is GLM-4.5-Air or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.