Model comparison
Codellama 70b Instruct vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.7 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 0 categories and Nova 2 Lite in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Nova 2 Lite leads 47.1 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Nova 2 Lite | |
|---|---|---|
| Provider | Meta | Amazon |
| Noometry Index | 33.7 | 39.7 |
| Released | — | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 7 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Codellama 70b Instruct: 37.6 (#193), Nova 2 Lite: 40.7 (#134)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1385 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Nova 2 Lite: 24.1 (#121)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Nova 2 Lite leads
Codellama 70b Instruct: 20.1 (#242), Nova 2 Lite: 27.5 (#118)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1364 |
Math Not comparable
Codellama 70b Instruct: —, Nova 2 Lite: 37.5 (#156)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Not comparable
Codellama 70b Instruct: —, Nova 2 Lite: 43.0 (#94)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1358 |
Multilingual Nova 2 Lite leads
Codellama 70b Instruct: 24.8 (#288), Nova 2 Lite: 47.1 (#153)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 992 | 1337 |
| LMArena Chinese | — | 1364 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1271 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1373 |
Instruction Following Nova 2 Lite leads
Codellama 70b Instruct: 51.9 (#293), Nova 2 Lite: 70.5 (#161)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1024 | 1335 |
Long Context Not comparable
Codellama 70b Instruct: —, Nova 2 Lite: 40.6 (#150)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | — | 1335 |
Writing & Preference Nova 2 Lite leads
Codellama 70b Instruct: 33.4 (#277), Nova 2 Lite: 53.9 (#154)
| Benchmark | Codellama 70b Instruct | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1057 | 1362 |
| LMArena Creative Writing | — | 1291 |
| LMArena Multi-Turn | — | 1338 |
Frequently asked questions
Is Codellama 70b Instruct better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Nova 2 Lite share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Nova 2 Lite has 19.