Model comparison
Codellama 70b Instruct vs Mistral Large 4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.7 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 0 categories and Mistral Large 4 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Large 4 leads 52.6 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Mistral Large 4 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 43.1 |
| Released | — | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.68 |
| Output $ / M tokens | — | $2.09 |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Codellama 70b Instruct: 37.6 (#193), Mistral Large 4: 48.6 (#57)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena WebDev | — | 1541 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1475 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Mistral Large 4 leads
Codellama 70b Instruct: 20.1 (#242), Mistral Large 4: 22.5 (#192)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1444 |
| NYT Connections (extended) | — | 27.4% |
Math Not comparable
Codellama 70b Instruct: —, Mistral Large 4: 40.4 (#91)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Math | — | 1488 |
Knowledge Not comparable
Codellama 70b Instruct: —, Mistral Large 4: 36.6 (#166)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | — | 20% |
| LMArena Expert | — | 1447 |
Multilingual Mistral Large 4 leads
Codellama 70b Instruct: 24.8 (#288), Mistral Large 4: 52.6 (#82)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 992 | 1415 |
| LMArena Chinese | — | 1491 |
| LMArena Russian | — | 1414 |
Instruction Following Mistral Large 4 leads
Codellama 70b Instruct: 51.9 (#293), Mistral Large 4: 75.0 (#76)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1424 |
Long Context Not comparable
Codellama 70b Instruct: —, Mistral Large 4: 43.6 (#89)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | — | 1429 |
Writing & Preference Mistral Large 4 leads
Codellama 70b Instruct: 33.4 (#277), Mistral Large 4: 60.4 (#97)
| Benchmark | Codellama 70b Instruct | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1057 | 1427 |
| LMArena Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1424 |
Frequently asked questions
Is Codellama 70b Instruct better than Mistral Large 4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mistral Large 4 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral Large 4 has 15.