Model comparison
Codellama 70b Instruct vs Gemini 2.0 Pro
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 33.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
GoogleSummary
- The widest gap is in instruction following, where Gemini 2.0 Pro leads 75.5 to 51.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Gemini 2.0 Pro | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.7 | 39.1 |
| Released | — | 2025-02-05 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 70b Instruct: 37.6 (#193), Gemini 2.0 Pro: 37.8 (#187)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| Aider Polyglot | — | 35.6% |
| BigCodeBench Instruct | 40.7% | — |
| LiveBench Coding | — | 63.5% |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Gemini 2.0 Pro leads
Codellama 70b Instruct: 20.1 (#242), Gemini 2.0 Pro: 22.3 (#198)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| EnigmaEval | — | 0.7% |
| LiveBench Reasoning | — | 60.1% |
| LMArena Hard Prompts | 1052 | — |
| LiveBench Data Analysis | — | 68% |
| Epoch Capabilities Index | — | 135.06 |
| LiveBench | — | 65.1% |
Math Not comparable
Codellama 70b Instruct: —, Gemini 2.0 Pro: 39.7 (#100)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Math | — | 71% |
| MATH Level 5 | — | 83.5% |
Knowledge Not comparable
Codellama 70b Instruct: —, Gemini 2.0 Pro: 36.5 (#167)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Confabulations | — | 18.4% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), Gemini 2.0 Pro: —
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Gemini 2.0 Pro leads
Codellama 70b Instruct: 51.9 (#293), Gemini 2.0 Pro: 75.5 (#59)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Instruction Following | — | 83.4% |
| LMArena Instruction Following | 1024 | — |
Long Context Not comparable
Codellama 70b Instruct: —, Gemini 2.0 Pro: 29.2 (#292)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| Fiction.LiveBench | — | 41.7% |
Writing & Preference Gemini 2.0 Pro leads
Codellama 70b Instruct: 33.4 (#277), Gemini 2.0 Pro: 52.7 (#165)
| Benchmark | Codellama 70b Instruct | Gemini 2.0 Pro |
|---|---|---|
| LMArena Text | 1057 | — |
| LiveBench Language | — | 44.9% |
Frequently asked questions
Is Codellama 70b Instruct better than Gemini 2.0 Pro?
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Gemini 2.0 Pro better for coding?
They score almost the same on coding (37.6 vs 37.8); test both on your own repository before choosing.
How many benchmarks do Codellama 70b Instruct and Gemini 2.0 Pro share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemini 2.0 Pro has 14.