Model comparison
Codellama 34b Instruct vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 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 Kimi K2.6 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.6 leads 68.5 to 28.2.
Side by side
| Codellama 34b Instruct | Kimi K2.6 | |
|---|---|---|
| Provider | Meta | Moonshot AI |
| Noometry Index | 30.8 | 47.7 |
| Released | — | 2026-04-20 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 14 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Codellama 34b Instruct: 28.5 (#314), Kimi K2.6: 50.7 (#43)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Coding | 1046 | 1488 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 1,093 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Kimi K2.6: 21.9 (#137)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Codellama 34b Instruct: 19.6 (#255), Kimi K2.6: 40.5 (#55)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1470 |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.05 |
Math Kimi K2.6 leads
Codellama 34b Instruct: 31.0 (#230), Kimi K2.6: 57.0 (#41)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1056 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, Kimi K2.6: 54.0 (#54)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
| LMArena Expert | — | 1491 |
Multimodal Not comparable
Codellama 34b Instruct: —, Kimi K2.6: 31.6 (#103)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Codellama 34b Instruct: 25.8 (#284), Kimi K2.6: 54.9 (#37)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1011 | 1446 |
| LMArena Chinese | 976 | 1521 |
| LMArena French | — | 1471 |
| LMArena German | — | 1450 |
| LMArena Japanese | — | 1443 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1464 |
Instruction Following Kimi K2.6 leads
Codellama 34b Instruct: 52.2 (#291), Kimi K2.6: 76.3 (#43)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1451 |
Long Context Kimi K2.6 leads
Codellama 34b Instruct: 30.9 (#284), Kimi K2.6: 44.9 (#52)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1013 | 1468 |
Writing & Preference Kimi K2.6 leads
Codellama 34b Instruct: 28.2 (#297), Kimi K2.6: 68.5 (#26)
| Benchmark | Codellama 34b Instruct | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1066 | 1455 |
| LMArena Creative Writing | 1032 | 1434 |
| LMArena Multi-Turn | 1015 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Codellama 34b Instruct better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Kimi K2.6 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Kimi K2.6 has 51.