Muse Spark 1.3 vs GPT-6 Luna vs GLM-5.3
GPT-6 Luna comes out ahead, 80 to 73 and 64 on our weighted score, and it is the cheaper option too.Muse Spark 1.3 comes out ahead, 86 to 81 and 74 on our weighted score, though GPT-6 Luna is 10× cheaper per token.
Meta
Muse Spark 1.3
73/100- ECI158.2
- Price$1.25 / $4.25
- Context1.05M
- Our pick
OpenAI
GPT-6 Luna
80/100- ECI156.5
- Price$0.10 / $0.50
- Context1.05M
Z.ai (Zhipu)
GLM-5.3
64/100- ECI157.1
- Price$1.40 / $4.40
- Context1M
- Our pick
Meta
Muse Spark 1.3
86/100- ECI158.2
- Price$1.25 / $4.25
- Context1.05M
OpenAI
GPT-6 Luna
81/100- ECI156.5
- Price$0.10 / $0.50
- Context1.05M
Z.ai (Zhipu)
GLM-5.3
74/100- ECI157.1
- Price$1.40 / $4.40
- Context1M
GPT-6 Luna is our pickMuse Spark 1.3 is our pick
GPT-6 Luna is the better all-round choice, scoring 80/100 against Muse Spark 1.3 (73) and GLM-5.3 (64). It leads on price. Muse Spark 1.3 wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Muse Spark 1.3 is the better all-round choice, scoring 86/100 against GPT-6 Luna (81) and GLM-5.3 (74). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityMuse Spark 1.3Capabilities Index (ECI): Muse Spark 1.3 158.2 · GLM-5.3 157.1 · GPT-6 Luna 156.5
- Lowest priceGPT-6 LunaGPT-6 Luna $0.20 · Muse Spark 1.3 $2.00 · GLM-5.3 $2.15 per 1M tokens (3:1 blend)
- Longest contextGPT-6 Luna and Muse Spark 1.3GPT-6 Luna 1,050,000 · Muse Spark 1.3 1,048,576 · GLM-5.3 1,000,000 tokens
- Widest inputsMuse Spark 1.3Muse Spark 1.3: Text, Images, PDFs, Audio, Video · GPT-6 Luna: Text, Images, PDFs · GLM-5.3: Text
- Self-hostingGLM-5.3Publishes downloadable weights
| Measure | Weight | Muse Spark 1.3 | GPT-6 Luna | GLM-5.3 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 86 | 84 | 85 |
| Price | 25% | 34 | 79 | 33 |
| Inputs & features | 15% | 100 | 80 | 45 |
| Context window | 10% | 65 | 65 | 64 |
| Overall | 100% | 73/100 | 80/100 | 64/100 |
| Measure | Weight | Muse Spark 1.3 | GPT-6 Luna | GLM-5.3 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 86 | 84 | 85 |
| Inputs & features | 20% | 100 | 80 | 45 |
| Context window | 13% | 65 | 65 | 64 |
| Overall | 100% | 86/100 | 81/100 | 74/100 |
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) | 158.2 (best) | 156.5 | 157.1 |
| ECI rank | #28 of 159 (best) | #38 of 159 | #34 of 159 |
| ECI confidence interval | 156.2–160.5 | 154.6–158.5 | 155.0–159.4 |
| ECI evaluation date | Sep 2, 2026 | Sep 22, 2026 | Aug 14, 2026 |
| Documented capabilities | 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. | OpenAI's most efficient model for focused, high-volume tasks | Flagship GLM model for long-horizon coding, agents, and complex project delivery |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | Not published | 90.5%max | 90.9%max (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 74.4%xhigh | 79.0%max (best) | 68.8%max |
| OTIS Mock AIME 2024–2025Competition mathematics | 99.2%xhigh (best) | 98.9%max | 91.1%max |
| SimpleQA VerifiedShort factual questions | Not published | 41.4%max (best) | 41.0%max |
| Publisher-reported benchmarks | |||
| GDPval-AA 2max effort | 1754EloReported resultSep 2, 2026 | Not published | 1769EloReported result |
| JobBenchmax effort | 64.9mean rubric scoreReported resultSep 2, 2026 | Not published | Not published |
| OSWorld 2.0 · 08.08max effort | 66.9mean partial scoreReported resultSep 2, 2026 | Not published | Not published |
| OSWorld 2.0 · 08.08max effort | 32binary completion rateReported resultSep 2, 2026 | Not published | Not published |
| DeepSearchQAmax effort | 90.3F1Reported resultSep 2, 2026 | Not published | Not published |
| Agentic IF Index · Meta internalmax effort | 57.8scoreReported resultSep 2, 2026 | Not published | Not published |
| AutomationBench · public v3 task setmax effort | 49.6pass@1Reported resultSep 2, 2026 | Not published | Not published |
| MRCR 2 · 8-needle, 256K-512Kmax effort | 98.5mean sequence-match ratioReported resultSep 2, 2026 | Not published | Not published |
| MRCR 2 · 8-needle, 512K-1Mmax effort | 98.1mean sequence-match ratioReported resultSep 2, 2026 | Not published | Not published |
| DeepSWE 1.1max effort | 75.4pass@1Reported resultSep 2, 2026 | Not published | Not published |
| SWE-Atlas Codebase QnAmax effort | 59.4pass@1Reported resultSep 2, 2026 | Not published | Not published |
| Terminal-Bench 2.1max effort | 88.8pass@1Reported resultSep 2, 2026 | Not published | 88.2pass@1Reported result |
| DeepSWE 1.1max effort | Not published | 66.6scoreReported resultSep 22, 2026 | Not published |
| Terminal-Bench 3.0max effort | Not published | Not published | 28.3avg@3Reported result |
| DeepSWE 1.1max effort; 6h timeout; 400K context | Not published | Not published | 66.9resolvedReported result |
| NL2Repomax effort | Not published | Not published | 58scoreReported result |
| ProgramBenchmax effort | Not published | Not published | 19almost solvedReported result |
| FrontierSWEmax effort | Not published | Not published | 78.1dominance scoreReported resultAug 14, 2026 |
| SWE-Marathon 1.1max effort; modified anti-cheat checks | Not published | Not published | 42.5scoreReported result |
| PostTrainBenchmax effort; 3 runs; modified external-API checks | Not published | Not published | 39.8weighted averageReported result |
| CyberGymmax effort | Not published | Not published | 84.5pass@1Reported result |
| ExploitGym · 869 tasksmax effort; 2h rescaled timeout | Not published | Not published | 105tasks solvedReported result |
| ExploitGym · 869 tasksmax effort; 6h rescaled timeout | Not published | Not published | 130tasks solvedReported result |
| ExploitBenchmax effort; union over 3 revisions | Not published | Not published | 54.4average coverageReported result |
| Toolathlon-Verifiedmax effort | Not published | Not published | 73pass@1Reported result |
| AutomationBench 1.0.6max effort | Not published | Not published | 48.2pass@1Reported result |
| Agents' Last Exammax effort; CLI | Not published | Not published | 28.5scoreReported result |
| Humanity's Last Exammax effort; with tools | Not published | Not published | 62.5accuracyReported result |
| Price per million tokens | |||
| Input | $1.25 | $0.10 (best) | $1.40 |
| Output | $4.25 | $0.50 (best) | $4.40 |
| Cached input | $0.15 | $0.01 (best) | $0.26 |
| Blended (3:1) | $2.00 | $0.20 (best) | $2.15 |
| Long-context rate | Same rate | Over 272K: $0.20 / $0.75 | Same rate |
| Price source | Official Meta API | Official OpenAI API | Official Z.AI API |
| Limits | |||
| Context window | 1,048,576 tokens | 1,050,000 tokens (best) | 1,000,000 tokens |
| Max input | Not published | 922,000 tokens | Not published |
| Max output | 131,072 tokens (best) | 128,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | Yes | Yes | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yesminimal · low · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max | Yeslow · high · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| File attachments | Yes | Yes | No |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | effort | effort | effort |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | muse-spark-1.3 | gpt-6-luna | glm-5.3 |
| API providers | 18 | 49 | 123 (best) |
| Released | Sep 2, 2026 | Sep 22, 2026 | Aug 14, 2026 |
| Knowledge cutoff | Not published | May 18, 2026 | Not published |
| Publisher documentation | Publisher documentation | Publisher documentation | Publisher documentation · Model weights |
| Source metadata updated | Sep 2, 2026 | Sep 22, 2026 | Aug 14, 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.
Muse Spark 1.3$21.00
GPT-6 Luna$2.00
GLM-5.3$22.80
Which should you choose?
Which is better: Muse Spark 1.3, GPT-6 Luna or GLM-5.3?
GPT-6 Luna is the better all-round choice, scoring 80/100 against Muse Spark 1.3 (73) and GLM-5.3 (64). It leads on price. Muse Spark 1.3 wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Muse Spark 1.3 is the better all-round choice, scoring 86/100 against GPT-6 Luna (81) and GLM-5.3 (74). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Muse Spark 1.3, GPT-6 Luna or GLM-5.3?
GPT-6 Luna is cheaper at $0.10 input / $0.50 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); GLM-5.3 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for GPT-6 Luna versus $2.00 for Muse Spark 1.3 (10× as much) and $2.15 for GLM-5.3 (11× 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), GLM-5.3 157.1 (#34 of 159) and GPT-6 Luna 156.5 (#38 of 159). The confidence ranges of the top two overlap (156.2–160.5 vs 155.0–159.4), so treat the gap as small. On individual benchmarks: FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, Muse Spark 1.3 74.4%, GLM-5.3 68.8%; OTIS Mock AIME 2024–2025 — Muse Spark 1.3 99.2%, GPT-6 Luna 98.9%, GLM-5.3 91.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Muse Spark 1.3, GPT-6 Luna and GLM-5.3 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-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 GLM-5.3. Maximum output per response: Muse Spark 1.3 up to 131,072, GPT-6 Luna up to 128,000, GLM-5.3 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Muse Spark 1.3 accepts text, images, PDFs, audio and video; GPT-6 Luna accepts text, images and PDFs; GLM-5.3 accepts text. Muse Spark 1.3 handles the widest range of inputs.
Are any of these open source?
GLM-5.3 publishes its weights and can be self-hosted; Muse Spark 1.3 and GPT-6 Luna is proprietary.
Which is newer?
GPT-6 Luna is the newest, released Sep 22, 2026. Muse Spark 1.3 came out Sep 2, 2026; GLM-5.3 came out Aug 14, 2026. Knowledge cutoff: GPT-6 Luna May 18, 2026.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.