Model comparison
Claude Opus 4.5 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.5 on the Noometry Index.
Last verified . 30 shared benchmarks.
MetaSummary
- They share 30 benchmarks with published results for both. Claude Opus 4.5 scores higher in 4 categories and Muse Spark 1.3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 38.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 4.9% for Claude Opus 4.5 and 46.3% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.5 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 50.5 | 54.8 |
| Released | 2025-11-01 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $5 | $1.25 |
| Output $ / M tokens | $25 | $4.25 |
| Results tracked | 69 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Claude Opus 4.5: 54.8 (#27), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1494 | 1657 |
| LMArena Coding | 1504 | 1514 |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | 76.8% | — |
| CursorBench | — | 41.6% |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 59.7% |
| GSO | 26.5% | — |
| WeirdML | 63.7% | — |
| ALE-Bench | 1,025 | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.3 (#12), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 63.1% | — |
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| GDP.pdf | — | 27.6% |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
| Vending-Bench 2 | 4,967 | — |
Reasoning Muse Spark 1.3 leads
Claude Opus 4.5: 42.6 (#51), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 52.5% | 85.1% |
| Chess Puzzles | 12% | 38% |
| LMArena Hard Prompts | 1476 | 1503 |
| Mystery Game Puzzles | 22% | 25% |
| DTBench | 89.9% | 96.5% |
| LMCA | 44.5% | 53.9% |
| Epoch Capabilities Index | 150.09 | 156.75 |
| ARC-AGI-2 | 37.6% | — |
| SimpleBench | 62% | — |
| Kagi LLM Benchmark | 80.2% | — |
| ARC-AGI-1 | 80% | — |
| CritPt | — | 26% |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 60.7 | — |
Math Muse Spark 1.3 leads
Claude Opus 4.5: 38.6 (#132), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 74.4% |
| FrontierMath Tier 4 | 4.9% | 46.3% |
| OTIS Mock AIME 2024-2025 | 86.1% | 99.2% |
| ProofBench | 36% | 58% |
| LMArena Math | 1463 | 1494 |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.5 leads
Claude Opus 4.5: 56.5 (#44), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1487 | 1516 |
| GPQA Diamond | 86% | — |
| Humanity's Last Exam | 25.2% | — |
| SimpleQA Verified | 45.7% | — |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Muse Spark 1.3 leads
Claude Opus 4.5: 31.4 (#107), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Document | 1462 | 1471 |
| LMArena Vision | — | 1309 |
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
Multilingual Muse Spark 1.3 leads
Claude Opus 4.5: 54.3 (#47), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1438 | 1481 |
| LMArena Chinese | 1470 | 1529 |
| LMArena French | 1471 | 1524 |
| LMArena German | 1449 | 1515 |
| LMArena Japanese | 1416 | 1474 |
| LMArena Korean | 1424 | 1501 |
| LMArena Russian | 1447 | 1490 |
| LMArena Spanish | 1458 | 1490 |
Instruction Following Too close to call
Claude Opus 4.5: 77.5 (#19), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1477 |
Long Context Too close to call
Claude Opus 4.5: 46.5 (#22), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1480 | 1488 |
| CL-bench | 21.1% | — |
Writing & Preference Muse Spark 1.3 leads
Claude Opus 4.5: 68.1 (#28), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Claude Opus 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1451 | 1490 |
| LMArena Creative Writing | 1445 | 1455 |
| EQ-Bench Creative Writing | 1687 | 1906 |
| LMArena Multi-Turn | 1466 | 1482 |
Frequently asked questions
Is Claude Opus 4.5 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.5 on the Noometry Index.
Which is cheaper, Claude Opus 4.5 or Muse Spark 1.3?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Claude Opus 4.5 lists at $5 and $25.
Is Claude Opus 4.5 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 54.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.5 and Muse Spark 1.3 share?
30 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Muse Spark 1.3 has 37.