Model comparison
Codellama 70b Instruct vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 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 Muse Spark 1.2 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.3 to 33.4.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Muse Spark 1.2 | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 33.7 | 50.3 |
| Released | — | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $4.25 |
| Results tracked | 7 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Codellama 70b Instruct: 37.6 (#193), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1495 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Muse Spark 1.2: 29.4 (#87)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Codellama 70b Instruct: 20.1 (#242), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1486 |
| SimpleBench | — | 74.5% |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 154.87 |
Math Not comparable
Codellama 70b Instruct: —, Muse Spark 1.2: 46.4 (#70)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | — | 1471 |
Knowledge Not comparable
Codellama 70b Instruct: —, Muse Spark 1.2: 54.1 (#53)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | — | 60.3% |
| LMArena Expert | — | 1480 |
Multimodal Not comparable
Codellama 70b Instruct: —, Muse Spark 1.2: 43.4 (#25)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |
Multilingual Muse Spark 1.2 leads
Codellama 70b Instruct: 24.8 (#288), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 992 | 1478 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1513 |
| LMArena Russian | — | 1487 |
| LMArena Spanish | — | 1498 |
Instruction Following Muse Spark 1.2 leads
Codellama 70b Instruct: 51.9 (#293), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1461 |
Long Context Not comparable
Codellama 70b Instruct: —, Muse Spark 1.2: 45.2 (#48)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | — | 1475 |
Writing & Preference Muse Spark 1.2 leads
Codellama 70b Instruct: 33.4 (#277), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Codellama 70b Instruct | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1057 | 1482 |
| LMArena Creative Writing | — | 1449 |
| EQ-Bench Creative Writing | — | 1840 |
| LMArena Multi-Turn | — | 1494 |
Frequently asked questions
Is Codellama 70b Instruct better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Muse Spark 1.2 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Muse Spark 1.2 has 31.