Model comparison
Muse Spark 1.2 vs Trinity Large Thinking
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.1 on the Noometry Index. Trinity Large Thinking costs 5.2× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Meta
Arcee AISummary
- They share 15 benchmarks with published results for both. Muse Spark 1.2 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 16.3.
- The biggest single-benchmark swing is NYT Connections (extended): 79.2% for Muse Spark 1.2 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.2 | Trinity Large Thinking | |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 49.8 | 38.1 |
| Released | 2026-08-05 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $1.25 | $0.25 |
| Output $ / M tokens | $4.25 | $0.80 |
| Results tracked | 28 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Muse Spark 1.2: 48.6 (#49), Trinity Large Thinking: 33.8 (#238)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1532 | 1238 |
| SciCode | 56.4% | 36.1% |
| LMArena Coding | 1497 | 1381 |
| DeepSWE | 54.9% | — |
| FrontierSWE | 12% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.2: 29.5 (#77), Trinity Large Thinking: —
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |
Reasoning Muse Spark 1.2 leads
Muse Spark 1.2: 50.4 (#32), Trinity Large Thinking: 16.3 (#298)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 79.2% | 16.5% |
| CritPt | 17.7% | 0.9% |
| LMArena Hard Prompts | 1490 | 1350 |
| SimpleBench | 74.5% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 155.18 | — |
Math Muse Spark 1.2 leads
Muse Spark 1.2: 43.8 (#68), Trinity Large Thinking: 34.9 (#149)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| ProofBench | 43% | — |
| LMArena Math | — | 1366 |
Knowledge Muse Spark 1.2 leads
Muse Spark 1.2: 53.9 (#49), Trinity Large Thinking: 40.3 (#107)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1485 | 1359 |
| SimpleQA Verified | 60.3% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Muse Spark 1.2: 42.6 (#24), Trinity Large Thinking: —
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual Muse Spark 1.2 leads
Muse Spark 1.2: 57.4 (#10), Trinity Large Thinking: 46.4 (#155)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1479 | 1325 |
| LMArena Chinese | 1519 | 1372 |
| LMArena Russian | 1494 | 1338 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1312 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1356 |
Instruction Following Muse Spark 1.2 leads
Muse Spark 1.2: 77.1 (#30), Trinity Large Thinking: 70.7 (#157)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1466 | 1334 |
Long Context Muse Spark 1.2 leads
Muse Spark 1.2: 45.4 (#35), Trinity Large Thinking: 41.2 (#139)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1483 | 1355 |
Writing & Preference Muse Spark 1.2 leads
Muse Spark 1.2: 72.6 (#14), Trinity Large Thinking: 54.0 (#152)
| Benchmark | Muse Spark 1.2 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1486 | 1340 |
| LMArena Creative Writing | 1444 | 1321 |
| LMArena Multi-Turn | 1504 | 1342 |
| EQ-Bench Creative Writing | 1840 | — |
Frequently asked questions
Is Muse Spark 1.2 better than Trinity Large Thinking?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.1 on the Noometry Index. Trinity Large Thinking costs 5.2× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, Muse Spark 1.2 or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Muse Spark 1.2 or Trinity Large Thinking better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 262K.
How many benchmarks do Muse Spark 1.2 and Trinity Large Thinking share?
15 benchmarks have published results for both models. Muse Spark 1.2 has 28 scored results on Noometry and Trinity Large Thinking has 24.