Model comparison
Codellama 34b Instruct vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Qwen3.8 27B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 28.2.
Side by side
| Codellama 34b Instruct | Qwen3.8 27B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 46.0 |
| Released | — | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 14 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Codellama 34b Instruct: 28.5 (#314), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1046 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Codellama 34b Instruct: 19.6 (#255), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Codellama 34b Instruct: 31.0 (#230), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1056 | 1456 |
| ProofBench | — | 16% |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen3.8 27B: 41.6 (#109)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |
Multimodal Not comparable
Codellama 34b Instruct: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Codellama 34b Instruct: 25.8 (#284), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1011 | 1430 |
| LMArena Chinese | 976 | 1504 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1448 |
Instruction Following Qwen3.8 27B leads
Codellama 34b Instruct: 52.2 (#291), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1439 |
Long Context Qwen3.8 27B leads
Codellama 34b Instruct: 30.9 (#284), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1013 | 1450 |
Writing & Preference Qwen3.8 27B leads
Codellama 34b Instruct: 28.2 (#297), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Codellama 34b Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1066 | 1441 |
| LMArena Creative Writing | 1032 | 1384 |
| LMArena Multi-Turn | 1015 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Qwen3.8 27B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen3.8 27B has 31.