Model comparison
Codellama 70b Instruct vs Command A
Command A is the stronger model overall, scoring 36.5 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
CohereSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Command A in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Command A leads 45.3 to 24.8.
Side by side
| Codellama 70b Instruct | Command A | |
|---|---|---|
| Provider | Meta | Cohere |
| Noometry Index | 33.7 | 36.5 |
| Released | — | 2025-03-13 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 8K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 7 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Command A: 27.2 (#322)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| Aider Polyglot | — | 12% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1330 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Command A: 35.9 (#40)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 57.1% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Command A: 18.3 (#283)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1326 |
| Kagi LLM Benchmark | — | 28.8% |
| DTBench | — | 61.3% |
| LMCA | — | 10.3% |
Math Not comparable
Codellama 70b Instruct: —, Command A: 36.2 (#171)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Math | — | 1300 |
Knowledge Not comparable
Codellama 70b Instruct: —, Command A: 37.1 (#159)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| Vectara Hallucination Rate | — | 9.3% |
| LMArena Expert | — | 1295 |
Multilingual Command A leads
Codellama 70b Instruct: 24.8 (#288), Command A: 45.3 (#170)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Non-English | 992 | 1313 |
| LMArena Chinese | — | 1327 |
| LMArena French | — | 1351 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1285 |
| LMArena Korean | — | 1285 |
| LMArena Russian | — | 1314 |
| LMArena Spanish | — | 1347 |
Instruction Following Command A leads
Codellama 70b Instruct: 51.9 (#293), Command A: 69.1 (#177)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Instruction Following | 1024 | 1309 |
Long Context Not comparable
Codellama 70b Instruct: —, Command A: 40.6 (#151)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Longer Query | — | 1334 |
Writing & Preference Command A leads
Codellama 70b Instruct: 33.4 (#277), Command A: 47.6 (#208)
| Benchmark | Codellama 70b Instruct | Command A |
|---|---|---|
| LMArena Text | 1057 | 1331 |
| LMArena Creative Writing | — | 1319 |
| EQ-Bench Creative Writing | — | 1145 |
| LMArena Multi-Turn | — | 1339 |
Frequently asked questions
Is Codellama 70b Instruct better than Command A?
Command A is the stronger model overall, scoring 36.5 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Command A better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 27.2 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Command A share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Command A has 24.