DeepSeek V4.1 Flash vs Muse Spark 1.3 vs GPT-5.6 Luna
Too close to call on our weighted score (DeepSeek V4.1 Flash 76, GPT-5.6 Luna 76, Muse Spark 1.3 68). The right pick depends on what you value most.Too close to call on our weighted score (Muse Spark 1.3 82, DeepSeek V4.1 Flash 81, GPT-5.6 Luna 81). The right pick depends on what you value most.
DeepSeek
DeepSeek V4.1 Flash
76/100- ECI157.0
- Price$0.222 / $1.04
- Context1M
Meta
Muse Spark 1.3
68/100- ECI158.2
- Price$1.25 / $4.25
- Context1.05M
OpenAI
GPT-5.6 Luna
76/100- ECI156.7
- Price$0.20 / $1.20
- Context1.05M
DeepSeek
DeepSeek V4.1 Flash
81/100- ECI157.0
- Price$0.222 / $1.04
- Context1M
Meta
Muse Spark 1.3
82/100- ECI158.2
- Price$1.25 / $4.25
- Context1.05M
OpenAI
GPT-5.6 Luna
81/100- ECI156.7
- Price$0.20 / $1.20
- Context1.05M
Too close to call
It is close. Our weighted score puts them within a point (DeepSeek V4.1 Flash 76/100, GPT-5.6 Luna 76/100, Muse Spark 1.3 68/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (Muse Spark 1.3 82/100, DeepSeek V4.1 Flash 81/100, GPT-5.6 Luna 81/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 83%, context window 17%.
- CapabilityMuse Spark 1.3Capabilities Index (ECI): Muse Spark 1.3 158.2 · DeepSeek V4.1 Flash 157.0 · GPT-5.6 Luna 156.7
- Lowest priceDeepSeek V4.1 FlashDeepSeek V4.1 Flash $0.426 · GPT-5.6 Luna $0.45 · Muse Spark 1.3 $2.00 per 1M tokens (3:1 blend)
- Longest contextGPT-5.6 Luna and Muse Spark 1.3GPT-5.6 Luna 1,050,000 · Muse Spark 1.3 1,048,576 · DeepSeek V4.1 Flash 1,000,000 tokens
- Widest inputsMuse Spark 1.3DeepSeek V4.1 Flash: Text, Images · Muse Spark 1.3: Text, Images, PDFs, Audio, Video · GPT-5.6 Luna: Text, Images, PDFs
- Self-hostingDeepSeek V4.1 FlashPublishes downloadable weights (MIT)
| Measure | Weight | DeepSeek V4.1 Flash | Muse Spark 1.3 | GPT-5.6 Luna |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 59% | 84 | 86 | 84 |
| Price | 29% | 65 | 34 | 63 |
| Context window | 12% | 64 | 65 | 65 |
| Overall | 100% | 76/100 | 68/100 | 76/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
| Measure | Weight | DeepSeek V4.1 Flash | Muse Spark 1.3 | GPT-5.6 Luna |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 83% | 84 | 86 | 84 |
| Context window | 17% | 64 | 65 | 65 |
| Overall | 100% | 81/100 | 82/100 | 81/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 157.0 | 158.2 (best) | 156.7 |
| ECI rank | #35 of 159 | #28 of 159 (best) | #37 of 159 |
| ECI confidence interval | 155.1–159.2 | 156.2–160.5 | 154.9–158.8 |
| ECI evaluation date | Sep 9, 2026 | Sep 2, 2026 | Jul 9, 2026 |
| Documented capabilities | DeepSeek V4.1 Flash model for reasoning and agentic coding | Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2. | Cost-efficient GPT-5.6 model for fast, high-volume workloads |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 89.8%max | Not published | 91.6%max (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 67.4%max | 74.4%xhigh | 82.1%max (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.3%max | 99.2%xhigh (best) | 98.3%max |
| SimpleQA VerifiedShort factual questions | 42.9%max (best) | Not published | 41.0%max |
| Publisher-reported benchmarks | |||
| GPQA Diamondreasoning_effort=100 | 90.9pass@1Reported result | Not published | Not published |
| MathArena Apexreasoning_effort=100 | 65.6pass@1Reported result | Not published | Not published |
| Humanity's Last Exam · full setreasoning_effort=100 | 36.8pass@1Reported result | Not published | Not published |
| Humanity's Last Exam · text-only subsetreasoning_effort=100 | 39.1pass@1Reported result | Not published | Not published |
| Codeforcesreasoning_effort=100 | 3471ratingReported result | Not published | Not published |
| Terminal-Bench 2.1reasoning_effort=100 | 90.6pass@1Reported result | Not published | Not published |
| Terminal-Bench 3.0reasoning_effort=100 | 30pass@1Reported result | Not published | Not published |
| Terminal-Bench 4.0reasoning_effort=100 | 31.2pass@1Reported result | Not published | Not published |
| DeepSWE 1.1reasoning_effort=100 | 74.2resolvedReported result | Not published | Not published |
| ProgramBenchreasoning_effort=100 | 20.3almost@1Reported result | Not published | Not published |
| NL2Reporeasoning_effort=100 | 64scoreReported result | Not published | Not published |
| CyberGymreasoning_effort=100 | 88.1pass@1Reported result | Not published | Not published |
| ExploitGymreasoning_effort=100 | 15.3pass@1Reported result | Not published | Not published |
| AutomationBenchreasoning_effort=100 | 54.8pass@1Reported result | Not published | Not published |
| Agents' Last Examreasoning_effort=100 | 31.8pass@1Reported result | Not published | Not published |
| SEC-Bench Proreasoning_effort=100 | 62.8pass@1Reported result | Not published | Not published |
| Humanity's Last Examreasoning_effort=100; with tools | 63.9pass@1Reported result | Not published | Not published |
| Chartographyreasoning_effort=100; with tools | 78.9pass@1Reported result | Not published | Not published |
| BabyVisionreasoning_effort=100; with tools | 89.6pass@1Reported result | Not published | Not published |
| ZeroBench · mainreasoning_effort=100; with tools | 49pass@5Reported result | Not published | Not published |
| GDPval-AA 2max effort | Not published | 1754EloReported resultSep 2, 2026 | Not published |
| JobBenchmax effort | Not published | 64.9mean rubric scoreReported resultSep 2, 2026 | Not published |
| OSWorld 2.0 · 08.08max effort | Not published | 66.9mean partial scoreReported resultSep 2, 2026 | Not published |
| OSWorld 2.0 · 08.08max effort | Not published | 32binary completion rateReported resultSep 2, 2026 | Not published |
| DeepSearchQAmax effort | Not published | 90.3F1Reported resultSep 2, 2026 | Not published |
| Agentic IF Index · Meta internalmax effort | Not published | 57.8scoreReported resultSep 2, 2026 | Not published |
| AutomationBench · public v3 task setmax effort | Not published | 49.6pass@1Reported resultSep 2, 2026 | Not published |
| MRCR 2 · 8-needle, 256K-512Kmax effort | Not published | 98.5mean sequence-match ratioReported resultSep 2, 2026 | Not published |
| MRCR 2 · 8-needle, 512K-1Mmax effort | Not published | 98.1mean sequence-match ratioReported resultSep 2, 2026 | Not published |
| DeepSWE 1.1max effort | Not published | 75.4pass@1Reported resultSep 2, 2026 | Not published |
| SWE-Atlas Codebase QnAmax effort | Not published | 59.4pass@1Reported resultSep 2, 2026 | Not published |
| Terminal-Bench 2.1max effort | Not published | 88.8pass@1Reported resultSep 2, 2026 | Not published |
| SWE-Bench ProPublisher-reported result | Not published | Not published | 62.7resolve rateReported resultJul 9, 2026 |
| Terminal-Bench 2.1Publisher-reported result | Not published | Not published | 84.7success rateReported resultJul 9, 2026 |
| DeepSWE 1.1Publisher-reported result | Not published | Not published | 67.2resolve rateReported resultJul 9, 2026 |
| GPQA DiamondPublisher-reported result | Not published | Not published | 92.3accuracyReported resultJul 9, 2026 |
| FrontierMath v2 · Tier 1-3Publisher-reported result | Not published | Not published | 78.6accuracyReported resultJul 9, 2026 |
| BrowseCompPublisher-reported result | Not published | Not published | 83.3accuracyReported resultJul 9, 2026 |
| OSWorld 2.0Publisher-reported result | Not published | Not published | 45.6success rateReported resultJul 9, 2026 |
| MMMU Prono tools | Not published | Not published | 78.4accuracyReported resultJul 9, 2026 |
| Agents' Last ExamPublisher-reported result | Not published | Not published | 50.3Reported resultJul 9, 2026 |
| ToolathlonPublisher-reported result | Not published | Not published | 53.4success rateReported resultJul 9, 2026 |
| Artificial Analysis Intelligence Index 4.1max | Not published | Not published | 51.2index scoreReported resultJul 9, 2026 |
| Artificial Analysis Coding Agent Index 1.1max | Not published | Not published | 74.6index scoreReported resultJul 9, 2026 |
| Price per million tokens | |||
| Input | $0.222 | $1.25 | $0.20 (best) |
| Output | $1.04 (best) | $4.25 | $1.20 |
| Cached input | Not published | $0.15 | $0.02 (best) |
| Blended (3:1) | $0.426 (best) | $2.00 | $0.45 |
| Long-context rate | Same rate | Same rate | Over 272K: $0.40 / $1.80 |
| Price source | Median of 82 providers | Official Meta API | Official OpenAI API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,048,576 tokens | 1,050,000 tokens (best) |
| Max input | Not published | Not published | 922,000 tokens |
| Max output | 384,000 tokens (best) | 131,072 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yesminimal · low · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Not published | Yes | Yes |
| File attachments | Yes | Yes | Yes |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | always | effort | effort |
| Availability | |||
| Weights | OpenMIT | Proprietary | Proprietary |
| API model ID | Not published | muse-spark-1.3 | gpt-5.6-luna |
| API providers | 86 (best) | 18 | 57 |
| Released | Sep 10, 2026 | Sep 2, 2026 | Jul 9, 2026 |
| Knowledge cutoff | May 2025 | Not published | Feb 16, 2026 |
| Publisher documentation | Model weights | Publisher documentation | Publisher documentation |
| Source metadata updated | Sep 10, 2026 | Sep 2, 2026 | Jul 9, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
DeepSeek V4.1 Flash$4.29
Muse Spark 1.3$21.00
GPT-5.6 Luna$4.40
Which should you choose?
Which is better: DeepSeek V4.1 Flash, Muse Spark 1.3 or GPT-5.6 Luna?
It is close. Our weighted score puts them within a point (DeepSeek V4.1 Flash 76/100, GPT-5.6 Luna 76/100, Muse Spark 1.3 68/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (Muse Spark 1.3 82/100, DeepSeek V4.1 Flash 81/100, GPT-5.6 Luna 81/100), so choose by what matters most for your work: Muse Spark 1.3 for raw capability and DeepSeek V4.1 Flash on price. The score weighs capability 83%, context window 17%.
Which is cheaper, DeepSeek V4.1 Flash, Muse Spark 1.3 or GPT-5.6 Luna?
DeepSeek V4.1 Flash is cheaper at $0.222 input / $1.04 output per million tokens (median across 82 API providers). GPT-5.6 Luna costs $0.20 input / $1.20 output per million tokens (official OpenAI API price); Muse Spark 1.3 costs $1.25 input / $4.25 output per million tokens (official Meta API price). At a typical mix of three input tokens to one output token, that is $0.426 per million tokens for DeepSeek V4.1 Flash versus $0.45 for GPT-5.6 Luna (1.1× as much) and $2.00 for Muse Spark 1.3 (4.7× as much).
Which scores higher on benchmarks?
Muse Spark 1.3 scores higher on the Capabilities Index (ECI): Muse Spark 1.3 158.2 (#28 of 159), DeepSeek V4.1 Flash 157.0 (#35 of 159) and GPT-5.6 Luna 156.7 (#37 of 159). The confidence ranges of the top two overlap (156.2–160.5 vs 155.1–159.2), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — GPT-5.6 Luna 82.1%, Muse Spark 1.3 74.4%, DeepSeek V4.1 Flash 67.4%; OTIS Mock AIME 2024–2025 — Muse Spark 1.3 99.2%, DeepSeek V4.1 Flash 98.3%, GPT-5.6 Luna 98.3%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4.1 Flash, Muse Spark 1.3 and GPT-5.6 Luna yet, so there is no like-for-like coding score. On overall capability, Muse Spark 1.3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-5.6 Luna and Muse Spark 1.3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4.1 Flash. Maximum output per response: DeepSeek V4.1 Flash up to 384,000, Muse Spark 1.3 up to 131,072, GPT-5.6 Luna up to 128,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4.1 Flash accepts text and images; Muse Spark 1.3 accepts text, images, PDFs, audio and video; GPT-5.6 Luna accepts text, images and PDFs. Muse Spark 1.3 handles the widest range of inputs.
Are any of these open source?
DeepSeek V4.1 Flash publishes its weights (MIT) and can be self-hosted; Muse Spark 1.3 and GPT-5.6 Luna is proprietary.
Which is newer?
DeepSeek V4.1 Flash is the newest, released Sep 10, 2026. Muse Spark 1.3 came out Sep 2, 2026; GPT-5.6 Luna came out Jul 9, 2026. Knowledge cutoff: DeepSeek V4.1 Flash May 2025, GPT-5.6 Luna Feb 16, 2026.
How do you decide the winner?
This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses capability (83%, independent benchmark results); context window (17%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.