Model comparison
GLM-4.7 vs Tulu 3 (Tülu 3) 70B
GLM-4.7 is the stronger model overall, scoring 42.0 to 33.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7 leads 38.6 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 4.4% for Tulu 3 (Tülu 3) 70B.
Side by side
| GLM-4.7 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 42.0 | 33.0 |
| Released | 2025-12-22 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 14 |
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), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1454 | 1235 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Tulu 3 (Tülu 3) 70B: —
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning Too close to call
GLM-4.7: 24.3 (#164), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1220 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 143.51 | — |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 4.4% |
| LMArena Math | 1423 | 1242 |
| ProofBench | 6% | — |
| MATH Level 5 | — | 42.7% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 83.3% | 46.3% |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| LMArena Expert | 1424 | — |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1417 | 1236 |
| LMArena Chinese | 1495 | 1249 |
| LMArena Russian | 1423 | 1246 |
| LMArena French | 1432 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1399 | — |
| LMArena Spanish | 1434 | — |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1233 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1432 | 1224 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | GLM-4.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1435 | 1256 |
| LMArena Creative Writing | 1401 | 1231 |
| LMArena Multi-Turn | 1446 | 1252 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Tulu 3 (Tülu 3) 70B?
GLM-4.7 is the stronger model overall, scoring 42.0 to 33.0 on the Noometry Index.
Is GLM-4.7 or Tulu 3 (Tülu 3) 70B better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 36.0 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.