Model comparison
Codellama 34b Instruct vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
Mistral AISummary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Mistral Small in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 28.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 46.6% for Mistral Small.
Side by side
| Codellama 34b Instruct | Mistral Small | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.8 | 33.4 |
| Released | — | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 14 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Codellama 34b Instruct: 28.5 (#314), Mistral Small: 34.0 (#247)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 29% | 36.1% |
| LMArena Coding | 1046 | 1362 |
| BigCodeBench Complete | 37.1% | 46.6% |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Mistral Small: 28.1 (#93)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Mistral Small: 19.8 (#250)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Mistral Small: 16.4 (#293)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Math | 1056 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge Not comparable
Codellama 34b Instruct: —, Mistral Small: 31.0 (#222)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1291 |
| MMLU | — | 68.7% |
Multimodal Not comparable
Codellama 34b Instruct: —, Mistral Small: 33.5 (#96)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Codellama 34b Instruct: 25.8 (#284), Mistral Small: 45.5 (#169)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Non-English | 1011 | 1315 |
| LMArena Chinese | 976 | 1340 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |
Instruction Following Mistral Small leads
Codellama 34b Instruct: 52.2 (#291), Mistral Small: 66.4 (#209)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1028 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
Codellama 34b Instruct: 30.9 (#284), Mistral Small: 40.4 (#156)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1013 | 1327 |
Writing & Preference Mistral Small leads
Codellama 34b Instruct: 28.2 (#297), Mistral Small: 52.5 (#171)
| Benchmark | Codellama 34b Instruct | Mistral Small |
|---|---|---|
| LMArena Text | 1066 | 1338 |
| LMArena Creative Writing | 1032 | 1305 |
| LMArena Multi-Turn | 1015 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Codellama 34b Instruct better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Mistral Small share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Mistral Small has 39.