Model comparison
Codellama 34b Instruct vs Gemini 1.0 Pro
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.3 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
GoogleSummary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Gemini 1.0 Pro in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 9.3.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | Gemini 1.0 Pro | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 27.3 |
| Released | — | 2023-12-13 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Codellama 34b Instruct: 28.5 (#314), Gemini 1.0 Pro: 32.2 (#275)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1046 | 1108 |
| HumanEval+ | 43.9% | 55.5% |
| MBPP+ | 56.3% | 61.4% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1109 |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 117.04 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Math | 1056 | 1132 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 11.2% |
Knowledge Not comparable
Codellama 34b Instruct: —, Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | — | 34% |
| LMArena Expert | — | 1059 |
| MMLU | — | 70% |
Multilingual Gemini 1.0 Pro leads
Codellama 34b Instruct: 25.8 (#284), Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1011 | 1138 |
| LMArena Chinese | 976 | 1124 |
| LMArena French | — | 1145 |
| LMArena German | — | 1125 |
| LMArena Japanese | — | 1023 |
| LMArena Russian | — | 1186 |
| LMArena Spanish | — | 1119 |
Instruction Following Gemini 1.0 Pro leads
Codellama 34b Instruct: 52.2 (#291), Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1028 | 1114 |
Long Context Gemini 1.0 Pro leads
Codellama 34b Instruct: 30.9 (#284), Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1013 | 1132 |
Writing & Preference Gemini 1.0 Pro leads
Codellama 34b Instruct: 28.2 (#297), Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | Codellama 34b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1066 | 1149 |
| LMArena Creative Writing | 1032 | 1131 |
| LMArena Multi-Turn | 1015 | 1139 |
Frequently asked questions
Is Codellama 34b Instruct better than Gemini 1.0 Pro?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 27.3 on the Noometry Index.
Is Codellama 34b Instruct or Gemini 1.0 Pro better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Gemini 1.0 Pro share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemini 1.0 Pro has 24.