Model comparison
Codellama 34b Instruct vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and GLM-5.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 66.9 to 28.2.
Side by side
| Codellama 34b Instruct | GLM-5.1 | |
|---|---|---|
| Provider | Meta | Z.ai (Zhipu) |
| Noometry Index | 30.8 | 47.8 |
| Released | — | 2026-04-07 |
| Weights | Open | Open |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 14 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Codellama 34b Instruct: 28.5 (#314), GLM-5.1: 48.7 (#55)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Coding | 1046 | 1485 |
| SWE-bench Verified | — | 74.2% |
| LMArena WebDev | — | 1508 |
| SciCode | — | 43.8% |
| WeirdML | — | 57.1% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 887.1 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, GLM-5.1: 24.9 (#113)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
Codellama 34b Instruct: 19.6 (#255), GLM-5.1: 39.1 (#60)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1472 |
| SimpleBench | — | 55.1% |
| NYT Connections (extended) | — | 77.7% |
| CritPt | — | 4.6% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| Epoch Capabilities Index | — | 149.84 |
Math GLM-5.1 leads
Codellama 34b Instruct: 31.0 (#230), GLM-5.1: 49.7 (#60)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Math | 1056 | 1473 |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 22.2% |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge Not comparable
Codellama 34b Instruct: —, GLM-5.1: 54.9 (#50)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
| LMArena Expert | — | 1476 |
Multilingual GLM-5.1 leads
Codellama 34b Instruct: 25.8 (#284), GLM-5.1: 55.0 (#36)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1011 | 1447 |
| LMArena Chinese | 976 | 1515 |
| LMArena French | — | 1474 |
| LMArena German | — | 1465 |
| LMArena Japanese | — | 1434 |
| LMArena Korean | — | 1418 |
| LMArena Russian | — | 1454 |
| LMArena Spanish | — | 1469 |
Instruction Following GLM-5.1 leads
Codellama 34b Instruct: 52.2 (#291), GLM-5.1: 76.3 (#42)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1451 |
Long Context GLM-5.1 leads
Codellama 34b Instruct: 30.9 (#284), GLM-5.1: 44.9 (#53)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1013 | 1466 |
Writing & Preference GLM-5.1 leads
Codellama 34b Instruct: 28.2 (#297), GLM-5.1: 66.9 (#31)
| Benchmark | Codellama 34b Instruct | GLM-5.1 |
|---|---|---|
| LMArena Text | 1066 | 1461 |
| LMArena Creative Writing | 1032 | 1453 |
| LMArena Multi-Turn | 1015 | 1472 |
| EQ-Bench Creative Writing | — | 1592 |
Frequently asked questions
Is Codellama 34b Instruct better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and GLM-5.1 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and GLM-5.1 has 41.