Model comparison
Codellama 34b Instruct vs Ministral 8B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Mistral AISummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Ministral 8B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Ministral 8B leads 39.6 to 28.2.
Side by side
| Codellama 34b Instruct | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.8 | 28.2 |
| Released | — | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 14 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Codellama 34b Instruct: 28.5 (#314), Ministral 8B: 35.0 (#230)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Coding | 1046 | 1202 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Ministral 8B: 16.4 (#148)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Ministral 8B: 18.4 (#281)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1191 |
| DTBench | — | 45.7% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Ministral 8B: 25.7 (#267)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Math | 1056 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Not comparable
Codellama 34b Instruct: —, Ministral 8B: 12.6 (#297)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
Multilingual Ministral 8B leads
Codellama 34b Instruct: 25.8 (#284), Ministral 8B: 35.1 (#247)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1011 | 1165 |
| LMArena Chinese | 976 | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Ministral 8B leads
Codellama 34b Instruct: 52.2 (#291), Ministral 8B: 60.5 (#250)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1161 |
Long Context Ministral 8B leads
Codellama 34b Instruct: 30.9 (#284), Ministral 8B: 36.7 (#227)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1013 | 1212 |
Writing & Preference Ministral 8B leads
Codellama 34b Instruct: 28.2 (#297), Ministral 8B: 39.6 (#246)
| Benchmark | Codellama 34b Instruct | Ministral 8B |
|---|---|---|
| LMArena Text | 1066 | 1191 |
| LMArena Creative Writing | 1032 | 1175 |
| LMArena Multi-Turn | 1015 | 1166 |
Frequently asked questions
Is Codellama 34b Instruct better than Ministral 8B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 28.2 on the Noometry Index.
Is Codellama 34b Instruct or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Ministral 8B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Ministral 8B has 17.