Model comparison
Codellama 70b Instruct vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Mercury in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mercury leads 41.6 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Mercury | |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 33.7 | 37.6 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Codellama 70b Instruct: 37.6 (#193), Mercury: 38.7 (#170)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1322 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), Mercury: 17.5 (#293)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
Multilingual Mercury leads
Codellama 70b Instruct: 24.8 (#288), Mercury: 41.6 (#206)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| LMArena Non-English | 992 | 1260 |
Instruction Following Mercury leads
Codellama 70b Instruct: 51.9 (#293), Mercury: 65.2 (#224)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| LMArena Instruction Following | 1024 | 1239 |
Long Context Not comparable
Codellama 70b Instruct: —, Mercury: 38.4 (#198)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |
Writing & Preference Mercury leads
Codellama 70b Instruct: 33.4 (#277), Mercury: 46.2 (#221)
| Benchmark | Codellama 70b Instruct | Mercury |
|---|---|---|
| LMArena Text | 1057 | 1282 |
| LMArena Creative Writing | — | 1191 |
| LMArena Multi-Turn | — | 1282 |
Frequently asked questions
Is Codellama 70b Instruct better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mercury share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mercury has 9.