Model comparison
Codellama 70b Instruct vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 33.3 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 Grok 4.20 Multi-Agent in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.1 to 33.6.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Meta | xAI |
| Noometry Index | 33.3 | 45.5 |
| Released | — | 2026-03-09 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 7 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Codellama 70b Instruct: 37.0 (#189), Grok 4.20 Multi-Agent: 42.4 (#91)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1458 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Grok 4.20 Multi-Agent: —
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
Codellama 70b Instruct: 19.2 (#241), Grok 4.20 Multi-Agent: 42.4 (#44)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1448 |
| NYT Connections (extended) | — | 89.6% |
Math Not comparable
Codellama 70b Instruct: —, Grok 4.20 Multi-Agent: 36.6 (#106)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | — | 1441 |
Knowledge Not comparable
Codellama 70b Instruct: —, Grok 4.20 Multi-Agent: 39.7 (#116)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | — | 1445 |
Multimodal Not comparable
Codellama 70b Instruct: —, Grok 4.20 Multi-Agent: 39.8 (#44)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual Grok 4.20 Multi-Agent leads
Codellama 70b Instruct: 24.9 (#283), Grok 4.20 Multi-Agent: 54.6 (#40)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 992 | 1440 |
| LMArena Chinese | — | 1475 |
| LMArena French | — | 1467 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1416 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1447 |
Instruction Following Grok 4.20 Multi-Agent leads
Codellama 70b Instruct: 52.1 (#288), Grok 4.20 Multi-Agent: 75.0 (#80)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1024 | 1420 |
Long Context Not comparable
Codellama 70b Instruct: —, Grok 4.20 Multi-Agent: 43.7 (#84)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | — | 1430 |
Writing & Preference Grok 4.20 Multi-Agent leads
Codellama 70b Instruct: 33.6 (#272), Grok 4.20 Multi-Agent: 64.1 (#57)
| Benchmark | Codellama 70b Instruct | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1057 | 1450 |
| LMArena Creative Writing | — | 1435 |
| LMArena Multi-Turn | — | 1451 |
Frequently asked questions
Is Codellama 70b Instruct better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or Grok 4.20 Multi-Agent better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Grok 4.20 Multi-Agent share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Grok 4.20 Multi-Agent has 20.