← comparisons · head to head
Muse Spark Open vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash scores higher than Muse Spark Open on all 5 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Muse Spark Open is at 16.7 and DeepSeek V4.1 Flash at 58.7 (out of 100).
Scores as published by each board; table composed November 13, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Muse Spark Open | DeepSeek V4.1 Flash | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,526.3 | 1,663.7 | DeepSeek V4.1 Flash |
| LiveBench global average (0-100) | 48.5 | 70.3 | DeepSeek V4.1 Flash |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 48.6 | 61.3 | DeepSeek V4.1 Flash |
| Artificial Analysis intelligence index · measured runs only | 24.9 | 32.6 | DeepSeek V4.1 Flash |
| Epoch AI Epoch Capabilities Index (ECI) · many benchmarks on one scale | 155.4 | 159.4 | DeepSeek V4.1 Flash |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Muse Spark Open is at 21.6 (#43 of 48) and DeepSeek V4.1 Flash at 70.4 (#13). DeepSeek V4.1 Flash scores higher on both coding boards that rate them.
| Coding board | Muse Spark Open | DeepSeek V4.1 Flash |
|---|---|---|
| LiveBench · Coding | 55.1 | 80.4 |
| Vals Vibe Code Bench | 76.2 | 87.7 |
Muse Spark Open at a glance
- Developer
- Meta
- Status
- Live since October 15, 2026
Live — Oct 15 · Meta's open-weights Spark: 816B total / 42B active mixture-of-experts with a 1.8B perception encoder, 1M context, text, image, video and audio in, text out · reasoning effort low / medium / high / xhigh, default xhigh · weights on Hugging Face in BF16 and NVFP4, gated, under Meta's Muse Model License · Meta says NVFP4 needs at least 700GB of VRAM and BF16 2TB, and that it is tuned to run on two M5 Ultra Mac Studios with MLX · OpenRouter: $1.25 / $4.25 per 1M through BaseTen (FP4), the same price as Muse Spark 1.3 · Meta's own table, against open-weight models: Artificial Analysis Intelligence Index 39, behind GLM 5.3 (45), Kimi K3 (44) and Qwen3.8 (40); ahead of all of them on JobBench (61.8) and MCP-Atlas (89.2); behind on Terminal-Bench 2.1 (76.4 vs Kimi K3's 85.0) · Artificial Analysis has no page of its own for it yet (Oct 15).
Meta releases Muse Spark Open: 816B open weights at $1.25 / $4.25, and its own table puts it behind Kimi K3 and GLM 5.3
2026-10-15 · Meta has released Muse Spark Open, an open-weights version of its Spark model: 816 billion parameters in total, 42 billion active per token, with a 1M-token context. Meta's model card on Hugging Face dates the release October 15.
DeepSeek V4.1 Flash at a glance
- Developer
- DeepSeek
- Status
- Live since September 10, 2026
Live — Sep 10 · 1M ctx · $0.15/$0.60 per 1M as our sweep read it, which is DeepSeek's off-peak rate (peak hours on weekdays cost double, $0.30/$1.20, per its pricing page) · DeepSeek serves it under the unversioned id deepseek-flash, so the id itself never carries the version · Oct 17: upgraded in place to the 1017 checkpoint (DeepSeek-V4.1-Flash-1017, per DeepSeek's changelog), same deepseek-flash id and price, web and app updated too; open weights on Hugging Face as deepseek-ai/DeepSeek-V4.1-Flash-1017 (MIT, same config.json as the Sep 10 weights); OpenRouter lists it as deepseek/deepseek-v4.1-flash-1017 at $0.15/$0.60, 1M ctx, 384K max output · Oct 19: the Vals Index (updated Oct 18) scores the 1017 build 56.58%, #14 of 50 and the top open-weight model there, up from 51.32% for the Sep 10 build; $0.64 per test on Vals' run, against $0.33 for the Sep 10 build · Oct 19: DHS ordered DeepSeek products, and third-party products built on DeepSeek, excluded from and removed from US federal civilian agencies (Federal Register 2026-21447, publishing Oct 20) · Oct 20: DeepSeek open-sourced DeepInfer (Apache-2.0), the inference engine it serves V4.1 Flash with, for NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs · Oct 20: Vals says the 1017 build completed 16.3 of 21 objectives on its coming offensive-cybersecurity benchmark, against 15.7 for GPT-6 Sol, on several times the tokens (a first finding; the full evaluation is due in the coming weeks).
DeepSeek open-sources DeepInfer, the engine behind V4.1 Flash, built for NVIDIA Blackwell and Huawei Ascend 950
2026-10-20 · DeepSeek released DeepInfer, the inference framework it says serves DeepSeek-V4.1-Flash at scale, as open source on October 20 under the Apache 2.0 license.
Vals: DeepSeek V4.1 Flash beat GPT-6 Sol on its offensive cybersecurity task, using about five times the tokens
2026-10-20 · Vals AI says DeepSeek V4.1 Flash 1017, an open-weight model, completed more objectives than OpenAI's GPT-6 Sol on a multi-step offensive cybersecurity task built on simulated corporate networks.
Muse Spark Open vs DeepSeek V4.1 Flash: quick answers
Which is better, Muse Spark Open or DeepSeek V4.1 Flash?
It depends on what you measure. DeepSeek V4.1 Flash scores higher than Muse Spark Open on all 5 public leaderboards that rate both. DeepSeek V4.1 Flash's widest lead is on Vals AI. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Muse Spark Open is at 16.7 and DeepSeek V4.1 Flash at 58.7 (out of 100).
Which is newer, Muse Spark Open or DeepSeek V4.1 Flash?
Muse Spark Open. It went live on October 15, 2026, 35 days after DeepSeek V4.1 Flash (September 10, 2026).
How do Muse Spark Open and DeepSeek V4.1 Flash compare for coding?
On the ArtificialWatch coding index, Muse Spark Open is at 21.6 (#43 of 48) and DeepSeek V4.1 Flash at 70.4 (#13). DeepSeek V4.1 Flash scores higher on both coding boards that rate them.
Who makes Muse Spark Open and DeepSeek V4.1 Flash?
Muse Spark Open is from Meta; DeepSeek V4.1 Flash is from DeepSeek.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed November 13, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear when the next one drops. Free.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire