Compare / head-to-head
Claude Sonnet 4.6vs
Muse Spark
Muse Spark leads 5 of 8 shared benchmarks.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 5
Muse Spark leads
Cheaper per token
—
list price, input + output
Larger context
—
both 1M tokens
Providers
2 providers
Anthropic · Meta
Claude Sonnet 4.6
Anthropic · released 2026-02-17
textvision
Muse Spark
Meta · released 2026-04-08
textvision
- Context
- —
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 19 · 8 core
Quality
Benchmark matrix
8 shared · 27 only Claude Sonnet 4.6 · 10 only Muse Spark| Benchmark | Claude Sonnet 4.6 | Muse Spark | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 8 | ||||
| SWE-bench Verified | 79.6% ↗ | 77.4% ↗ | +2.2 pt | Claude Sonnet 4.6 |
| GPQA Diamond | 89.9% ↗ | 89.5% ↗ | +0.4 pt | Claude Sonnet 4.6 |
| Humanity's Last Exam (no tools) | 33.2% ↗ | 42.8% ↗ | -9.6 pt | Muse Spark |
| LMArena Elo | 1458.3 ↗ | 1489.3 ↗ | -31 | Muse Spark |
| Humanity's Last Exam (with tools) | 49% ↗ | 50.4% ↗ | -1.4 pt | Muse Spark |
| LMArena Vision (LMArena) | 1275.2 ↗ | 1293.6 ↗ | -18.4 | Muse Spark |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 85.8% ↗epoch run | 88.9% ↗epoch run | -3.1 pt | Muse Spark |
| Terminal-Bench 2.0 | 59.1% ↗ | 59% ↗ | +0.1 pt | Claude Sonnet 4.6 |
| Only Claude Sonnet 4.6 reports · 27 | ||||
| APEX-Agents (Mercor) | 43% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 58.3% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 13% ↗epoch run | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 29.9% ↗ | not reported | — | — |
| GDPval-AA | 1633 ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 42.6% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 79.3% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 77.9% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 63.2% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 76.1% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 87% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 84.8% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1521.4 ↗ | not reported | — | — |
| MCP Atlas | 61.3% ↗ | not reported | — | — |
| MMMLU | 89.3% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 74.5% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 75.6% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 16% ↗epoch run | not reported | — | — |
| OSWorld-Verified | 72.5% ↗ | not reported | — | — |
| OSWorld-Verified (XLANG) | 72.1% ↗ | not reported | — | — |
| SAGE (Vals AI) | 46.6% ↗ | not reported | — | — |
| SimpleQA Verified | 35.5% ↗epoch run | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 75.2% ↗epoch run | not reported | — | — |
| Tau2-bench Retail | 91.7% ↗ | not reported | — | — |
| Tau2-bench Telecom | 97.9% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 7204.14 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 66.1% ↗ | not reported | — | — |
| Only Muse Spark reports · 10 | ||||
| ARC AGI 2 (Public) | not reported | 42.5% ↗ | — | — |
| CharXiv Reasoning | not reported | 86.4% ↗ | — | — |
| DeepSearchQA | not reported | 74.8% ↗ | — | — |
| HealthBench Hard | not reported | 42.8% ↗ | — | — |
| LiveCodeBench Pro | not reported | 80% ↗ | — | — |
| MedXpertQA (MM) | not reported | 78.4% ↗ | — | — |
| MMMU Pro | not reported | 80.4% ↗ | — | — |
| ScreenSpot Pro (With Python) | not reported | 84.1% ↗ | — | — |
| SimpleVQA | not reported | 71.3% ↗ | — | — |
| SWE-Bench Pro | not reported | 52.4% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Sonnet 4.6 minus Muse Spark in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Sonnet 4.6 | Muse Spark | Edge |
|---|---|---|---|
| Context window | 1M tokens | — | — |
| Max output | 128K tokens | — | — |
| Input price / 1M | $3 ↗ | — | — |
| Output price / 1M | $15 ↗ | — | — |
| Cached input / 1M | $0.3 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | — | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-17 | 2026-04-08 | — |
| Cited benchmark scores | 41 | 19 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Sonnet 4.6 vs …
Models sharing the most benchmarksMore matchups
Muse Spark vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 4.6 and Muse Spark on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.