Model comparison
Codellama 70b Instruct vs Ministral 8B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.2 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Mistral AISummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Ministral 8B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Ministral 8B leads 35.1 to 24.8.
Side by side
| Codellama 70b Instruct | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 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 | 7 | 17 |
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), Ministral 8B: 35.0 (#230)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1202 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Ministral 8B: 16.4 (#148)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Ministral 8B: 18.4 (#281)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1191 |
| DTBench | — | 45.7% |
Math Not comparable
Codellama 70b Instruct: —, Ministral 8B: 25.7 (#267)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Math | — | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Not comparable
Codellama 70b Instruct: —, Ministral 8B: 12.6 (#297)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
Multilingual Ministral 8B leads
Codellama 70b Instruct: 24.8 (#288), Ministral 8B: 35.1 (#247)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Non-English | 992 | 1165 |
| LMArena Chinese | — | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Ministral 8B leads
Codellama 70b Instruct: 51.9 (#293), Ministral 8B: 60.5 (#250)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1161 |
Long Context Not comparable
Codellama 70b Instruct: —, Ministral 8B: 36.7 (#227)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Longer Query | — | 1212 |
Writing & Preference Ministral 8B leads
Codellama 70b Instruct: 33.4 (#277), Ministral 8B: 39.6 (#246)
| Benchmark | Codellama 70b Instruct | Ministral 8B |
|---|---|---|
| LMArena Text | 1057 | 1191 |
| LMArena Creative Writing | — | 1175 |
| LMArena Multi-Turn | — | 1166 |
Frequently asked questions
Is Codellama 70b Instruct better than Ministral 8B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 28.2 on the Noometry Index.
Is Codellama 70b Instruct or Ministral 8B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 35.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Ministral 8B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Ministral 8B has 17.