Compare / head-to-head
DeepSeek V4 Flashvs
Muse Spark 1.3
Muse Spark 1.3 leads 15 of 16 shared benchmarks. Muse Spark 1.3 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 15
Muse Spark 1.3 leads
Cheaper per token
—
list price, input + output
Larger context
Muse Spark 1.3
1.0M tokens
Providers
2 providers
DeepSeek · Meta
DeepSeek V4 Flash
DeepSeek · released 2026-07-31
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 28 · 7 core
Muse Spark 1.3
Meta · released 2026-09-02
textvisionvideo
Quality
Benchmark matrix
16 shared · 12 only DeepSeek V4 Flash · 13 only Muse Spark 1.3| Benchmark | DeepSeek V4 Flash | Muse Spark 1.3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 16 | ||||
| LMArena Elo | 1436 ↗ | 1494.3 ↗ | -58.3 | Muse Spark 1.3 |
| Chess Puzzles (Epoch AI run) | 33% ↗epoch run | 38% ↗epoch run | -5 pt | Muse Spark 1.3 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 24.4% ↗epoch run | 46.3% ↗epoch run | -21.9 pt | Muse Spark 1.3 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 57.5% ↗epoch run | 74.4% ↗epoch run | -16.9 pt | Muse Spark 1.3 |
| LiveBench Agentic Coding (LiveBench) | 46.8% ↗ | 64.1% ↗ | -17.3 pt | Muse Spark 1.3 |
| LiveBench Coding (LiveBench) | 75% ↗ | 81.1% ↗ | -6.1 pt | Muse Spark 1.3 |
| LiveBench Data Analysis (LiveBench) | 79.3% ↗ | 79.6% ↗ | -0.3 pt | Muse Spark 1.3 |
| LiveBench Instruction Following (LiveBench) | 65.5% ↗ | 78% ↗ | -12.5 pt | Muse Spark 1.3 |
| LiveBench Language (LiveBench) | 79.2% ↗ | 82.8% ↗ | -3.6 pt | Muse Spark 1.3 |
| LiveBench Mathematics (LiveBench) | 86.8% ↗ | 95.9% ↗ | -9.1 pt | Muse Spark 1.3 |
| LiveBench Reasoning (LiveBench) | 86.6% ↗ | 89.7% ↗ | -3.1 pt | Muse Spark 1.3 |
| LMArena WebDev (LMArena) | 1581 ↗ | 1656.6 ↗ | -75.6 | Muse Spark 1.3 |
| Mystery Game Puzzles (Epoch AI run) | 34% ↗epoch run | 25% ↗epoch run | +9 pt | DeepSeek V4 Flash |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch run | 99.2% ↗epoch run | -4.8 pt | Muse Spark 1.3 |
| SimpleBench (SimpleBench) | 61.1% ↗ | 81.8% ↗ | -20.7 pt | Muse Spark 1.3 |
| Terminal-Bench 4.0 (Vals AI) | 18.7% ↗ | 24.7% ↗ | -6 pt | Muse Spark 1.3 |
| Only DeepSeek V4 Flash reports · 12 | ||||
| GPQA Diamond | 91% ↗epoch run | not reported | — | — |
| Agents' Last Exam | 25.2% ↗ | not reported | — | — |
| AutomationBench Public | 25.1% ↗ | not reported | — | — |
| Cybergym | 76.7% ↗ | not reported | — | — |
| DeepSWE | 54.4% ↗ | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 53.3% ↗ | not reported | — | — |
| NL2Repo | 54.2% ↗ | not reported | — | — |
| SimpleQA Verified | 33.6% ↗epoch run | not reported | — | — |
| Terminal Bench 2.1 | 82.7% ↗ | not reported | — | — |
| Toolathlon-Verified | 70.3% ↗ | not reported | — | — |
| Toolathlon-Verified (HKUST) | 70.7% ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 63% ↗ | not reported | — | — |
| Only Muse Spark 1.3 reports · 13 | ||||
| APEX-Agents (Mercor) | not reported | 57.8% ↗ | — | — |
| AutomationBench | not reported | 49.6% ↗ | — | — |
| DeepSearchQA | not reported | 90.3% ↗ | — | — |
| DeepSWE v1.1 | not reported | 75.4% ↗ | — | — |
| GDPval-AA v2 | not reported | 1754 ↗ | — | — |
| JobBench | not reported | 64.9% ↗ | — | — |
| LMArena Agent (LMArena) | not reported | 0.04 ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1290.2 ↗ | — | — |
| MRCR 256K-512K | not reported | 98.5% ↗ | — | — |
| MRCR 512K-1M | not reported | 98.1% ↗ | — | — |
| OSWorld 2.0 (partial) | not reported | 66.9% ↗ | — | — |
| SWE-Atlas Codebase QnA | not reported | 59.4% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 88.8% ↗ | — | — |
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 DeepSeek V4 Flash minus Muse Spark 1.3 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 | DeepSeek V4 Flash | Muse Spark 1.3 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Muse Spark 1.3 |
| Max output | — | — | — |
| Input price / 1M | — | $1.25 ↗ | — |
| Output price / 1M | — | $4.25 ↗ | — |
| Cached input / 1M | — | $0.15 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $5.5 | — |
| Modalities | text | text · vision · video | Muse Spark 1.3 |
| Released | 2026-07-31 | 2026-09-02 | — |
| Cited benchmark scores | 28 | 29 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V4 Flash vs …
Models sharing the most benchmarksMore matchups
Muse Spark 1.3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V4 Flash and Muse Spark 1.3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.