Model comparison
Codellama 70b Instruct vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GLM-4.7 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.7 leads 53.0 to 24.9.
Side by side
| Codellama 70b Instruct | GLM-4.7 | |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 33.3 | 41.7 |
| Released | — | 2025-12-22 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 7 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
Codellama 70b Instruct: 37.0 (#189), GLM-4.7: 43.6 (#74)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1454 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 399.48 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, GLM-4.7: 26.4 (#96)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
Codellama 70b Instruct: 19.2 (#241), GLM-4.7: 23.7 (#161)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1443 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 143.53 |
Math Not comparable
Codellama 70b Instruct: —, GLM-4.7: 37.7 (#92)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| LMArena Math | — | 1423 |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
Codellama 70b Instruct: —, GLM-4.7: 47.0 (#74)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |
| LMArena Expert | — | 1424 |
Multilingual GLM-4.7 leads
Codellama 70b Instruct: 24.9 (#283), GLM-4.7: 53.0 (#75)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 992 | 1417 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1432 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1439 |
| LMArena Korean | — | 1401 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1433 |
Instruction Following GLM-4.7 leads
Codellama 70b Instruct: 52.1 (#288), GLM-4.7: 74.6 (#90)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1411 |
Long Context Not comparable
Codellama 70b Instruct: —, GLM-4.7: 42.8 (#111)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
| LMArena Longer Query | — | 1432 |
Writing & Preference GLM-4.7 leads
Codellama 70b Instruct: 33.6 (#272), GLM-4.7: 61.1 (#89)
| Benchmark | Codellama 70b Instruct | GLM-4.7 |
|---|---|---|
| LMArena Text | 1057 | 1436 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1413 |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is Codellama 70b Instruct better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and GLM-4.7 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GLM-4.7 has 36.