Model comparison
Mercury 2 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 39.1 on the Noometry Index. Mercury 2 costs 5.3× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Muse Spark 1.3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.3 leads 54.0 to 23.8.
- The biggest single-benchmark swing is CritPt: 0.8% for Mercury 2 and 26% for Muse Spark 1.3.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 128K.
Side by side
| Mercury 2 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Inception | Meta |
| Noometry Index | 39.1 | 54.8 |
| Released | 2026-02-20 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 50K | 131K |
| Input $ / M tokens | $0.25 | $1.25 |
| Output $ / M tokens | $0.75 | $4.25 |
| Results tracked | 17 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Mercury 2: 33.5 (#255), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1171 | 1657 |
| SciCode | 38.7% | 59.7% |
| LMArena Coding | 1391 | 1514 |
| CursorBench | — | 41.6% |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Mercury 2: 23.8 (#170), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0.8% | 26% |
| LMArena Hard Prompts | 1362 | 1503 |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Not comparable
Mercury 2: —, Muse Spark 1.3: 73.1 (#21)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 58% |
| LMArena Math | — | 1494 |
Knowledge Muse Spark 1.3 leads
Mercury 2: 36.2 (#172), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1358 | 1516 |
| Vectara Hallucination Rate | 12.3% | — |
Multimodal Not comparable
Mercury 2: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Mercury 2: 46.6 (#157), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1331 | 1481 |
| LMArena Chinese | 1417 | 1529 |
| LMArena Russian | 1304 | 1490 |
| LMArena French | — | 1524 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Spanish | — | 1490 |
Instruction Following Muse Spark 1.3 leads
Mercury 2: 70.2 (#165), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1329 | 1477 |
Long Context Muse Spark 1.3 leads
Mercury 2: 40.5 (#154), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1330 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Mercury 2: 53.8 (#155), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Mercury 2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1355 | 1490 |
| LMArena Creative Writing | 1289 | 1455 |
| LMArena Multi-Turn | 1358 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is Mercury 2 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 39.1 on the Noometry Index. Mercury 2 costs 5.3× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Mercury 2 or Muse Spark 1.3?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Mercury 2 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 128K.
How many benchmarks do Mercury 2 and Muse Spark 1.3 share?
14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Muse Spark 1.3 has 37.