Model comparison
Codellama 70b Instruct vs Gemini 1.5 Pro (May 2024)
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.1 on the Noometry Index.
Last verified . 7 shared benchmarks.
Meta
GoogleSummary
- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Gemini 1.5 Pro (May 2024) in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 1.5 Pro (May 2024) leads 45.3 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 57.5% for Gemini 1.5 Pro (May 2024).
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.7 | 32.1 |
| Released | — | 2024-02-15 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 45 |
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), Gemini 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 43.8% |
| BigCodeBench Complete | 49.6% | 57.5% |
| HumanEval+ | 65.9% | 79.3% |
| WeirdML | — | 22.2% |
| LMArena Coding | — | 1294 |
| CadEval | — | 34% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1296 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 27.1% |
| DTBench | — | 59% |
| BIG-Bench Hard | — | 89.2% |
| Epoch Capabilities Index | — | 131.73 |
| ForecastBench | — | 58.4 |
Math Not comparable
Codellama 70b Instruct: —, Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 23.1% |
| Omni-MATH | — | 36.4% |
| LMArena Math | — | 1315 |
| MATH Level 5 | — | 70.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | — | 57.2% |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| GPQA (HELM) | — | 53.4% |
| LMArena Expert | — | 1279 |
| MMLU | — | 86.9% |
Multimodal Not comparable
Codellama 70b Instruct: —, Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
Multilingual Gemini 1.5 Pro (May 2024) leads
Codellama 70b Instruct: 24.8 (#288), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 992 | 1312 |
| LMArena Chinese | — | 1331 |
| LMArena French | — | 1302 |
| LMArena German | — | 1286 |
| LMArena Japanese | — | 1292 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1320 |
| LMArena Spanish | — | 1311 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Codellama 70b Instruct: 51.9 (#293), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1024 | 1297 |
| IFEval | — | 83.7% |
Long Context Not comparable
Codellama 70b Instruct: —, Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | — | 1308 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Codellama 70b Instruct: 33.4 (#277), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | Codellama 70b Instruct | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1057 | 1319 |
| LMArena Creative Writing | — | 1333 |
| WildBench | — | 81.3% |
| LMArena Multi-Turn | — | 1296 |
Frequently asked questions
Is Codellama 70b Instruct better than Gemini 1.5 Pro (May 2024)?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.1 on the Noometry Index.
Is Codellama 70b Instruct or Gemini 1.5 Pro (May 2024) 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 Gemini 1.5 Pro (May 2024) share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.