Model comparison
GLM-5 vs Tulu 3 (Tülu 3) 70B
GLM-5 is the stronger model overall, scoring 46.1 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-5 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 4.4% for Tulu 3 (Tülu 3) 70B.
Side by side
| GLM-5 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 46.1 | 33.0 |
| Released | 2026-02-11 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1461 | 1235 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Tulu 3 (Tülu 3) 70B: —
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| 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), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1220 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| Chess Puzzles | 10% | — |
| Epoch Capabilities Index | 145.83 | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 4.4% |
| LMArena Math | 1440 | 1242 |
| MathArena Final-Answer Competitions | 65.7% | — |
| MATH Level 5 | — | 42.7% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 87.8% | 46.3% |
| Vectara Hallucination Rate | 10.1% | — |
| LMArena Expert | 1454 | — |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1430 | 1236 |
| LMArena Chinese | 1511 | 1249 |
| LMArena Russian | 1436 | 1246 |
| LMArena French | 1455 | — |
| LMArena German | 1445 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1423 | — |
| LMArena Spanish | 1454 | — |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1428 | 1233 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1446 | 1224 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | GLM-5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1446 | 1256 |
| LMArena Creative Writing | 1439 | 1231 |
| LMArena Multi-Turn | 1456 | 1252 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Tulu 3 (Tülu 3) 70B?
GLM-5 is the stronger model overall, scoring 46.1 to 33.0 on the Noometry Index.
Is GLM-5 or Tulu 3 (Tülu 3) 70B better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 36.0 in the Noometry coding category.
How many benchmarks do GLM-5 and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.