Model comparison
Codellama 70b Instruct vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 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 1 category and Mistral Medium in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Medium leads 52.1 to 24.8.
Side by side
| Codellama 70b Instruct | Mistral Medium | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 36.3 |
| Released | — | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 7 | 36 |
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), Mistral Medium: 34.2 (#243)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1434 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Mistral Medium: 28.3 (#90)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Mistral Medium leads
Codellama 70b Instruct: 20.1 (#242), Mistral Medium: 24.0 (#167)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math Not comparable
Codellama 70b Instruct: —, Mistral Medium: 28.1 (#245)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| LMArena Math | — | 1408 |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
Codellama 70b Instruct: —, Mistral Medium: 25.0 (#265)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
Codellama 70b Instruct: —, Mistral Medium: 35.3 (#88)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Codellama 70b Instruct: 24.8 (#288), Mistral Medium: 52.1 (#91)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Non-English | 992 | 1408 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |
Instruction Following Mistral Medium leads
Codellama 70b Instruct: 51.9 (#293), Mistral Medium: 73.7 (#116)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1024 | 1398 |
Long Context Not comparable
Codellama 70b Instruct: —, Mistral Medium: 42.9 (#114)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1406 |
Writing & Preference Mistral Medium leads
Codellama 70b Instruct: 33.4 (#277), Mistral Medium: 60.0 (#103)
| Benchmark | Codellama 70b Instruct | Mistral Medium |
|---|---|---|
| LMArena Text | 1057 | 1424 |
| LMArena Creative Writing | — | 1391 |
| Short-Story Creative Writing | — | 77.3% |
| LMArena Multi-Turn | — | 1418 |
Frequently asked questions
Is Codellama 70b Instruct better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Mistral Medium better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.2 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mistral Medium share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral Medium has 36.