GPT-6 Luna vs GLM-5.3 vs DeepSeek V4 Flash 0731
Too close to call on our weighted score (GPT-6 Luna 80, DeepSeek V4 Flash 0731 80, GLM-5.3 67). The right pick depends on what you value most.Too close to call on our weighted score (GLM-5.3 81, GPT-6 Luna 81, DeepSeek V4 Flash 0731 79). The right pick depends on what you value most.
OpenAI
GPT-6 Luna
80/100- ECI156.5
- Price$0.10 / $0.50
- Context1.05M
Z.ai (Zhipu)
GLM-5.3
67/100- ECI157.1
- Price$1.40 / $4.40
- Context1M
DeepSeek
DeepSeek V4 Flash 0731
80/100- ECI154.4
- Price$0.14 / $0.30
- Context1M
OpenAI
GPT-6 Luna
81/100- ECI156.5
- Price$0.10 / $0.50
- Context1.05M
Z.ai (Zhipu)
GLM-5.3
81/100- ECI157.1
- Price$1.40 / $4.40
- Context1M
DeepSeek
DeepSeek V4 Flash 0731
79/100- ECI154.4
- Price$0.14 / $0.30
- Context1M
Too close to call
It is close. Our weighted score puts them within a point (GPT-6 Luna 80/100, DeepSeek V4 Flash 0731 80/100, GLM-5.3 67/100), so choose by what matters most for your work: GLM-5.3 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (GLM-5.3 81/100, GPT-6 Luna 81/100, DeepSeek V4 Flash 0731 79/100), so choose by what matters most for your work: GLM-5.3 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 83%, context window 17%.
- CapabilityGLM-5.3Capabilities Index (ECI): GLM-5.3 157.1 · GPT-6 Luna 156.5 · DeepSeek V4 Flash 0731 154.4
- Lowest priceDeepSeek V4 Flash 0731DeepSeek V4 Flash 0731 $0.18 · GPT-6 Luna $0.20 · GLM-5.3 $2.15 per 1M tokens (3:1 blend)
- Longest contextGPT-6 LunaGPT-6 Luna 1,050,000 · GLM-5.3 1,000,000 · DeepSeek V4 Flash 0731 1,000,000 tokens
- Widest inputsGPT-6 LunaGPT-6 Luna: Text, Images, PDFs · GLM-5.3: Text · DeepSeek V4 Flash 0731: Text
- Self-hostingGLM-5.3 and DeepSeek V4 Flash 0731Publishes downloadable weights (MIT)
| Measure | Weight | GPT-6 Luna | GLM-5.3 | DeepSeek V4 Flash 0731 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 59% | 84 | 85 | 82 |
| Price | 29% | 79 | 33 | 81 |
| Context window | 12% | 65 | 64 | 64 |
| Overall | 100% | 80/100 | 67/100 | 80/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
| Measure | Weight | GPT-6 Luna | GLM-5.3 | DeepSeek V4 Flash 0731 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 83% | 84 | 85 | 82 |
| Context window | 17% | 65 | 64 | 64 |
| Overall | 100% | 81/100 | 81/100 | 79/100 |
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) | 156.5 | 157.1 (best) | 154.4 |
| ECI rank | #38 of 159 | #34 of 159 (best) | #53 of 159 |
| ECI confidence interval | 154.6–158.5 | 155.0–159.4 | 152.6–156.4 |
| ECI evaluation date | Sep 22, 2026 | Aug 14, 2026 | Jul 31, 2026 |
| Documented capabilities | OpenAI's most efficient model for focused, high-volume tasks | Flagship GLM model for long-horizon coding, agents, and complex project delivery | Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 90.5%max | 90.9%max | 91.0%max (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 79.0%max (best) | 68.8%max | 57.5%max |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.9%max (best) | 91.1%max | 94.4%max |
| SimpleQA VerifiedShort factual questions | 41.4%max (best) | 41.0%max | 33.6%max |
| Publisher-reported benchmarks | |||
| DeepSWE 1.1max effort | 66.6scoreReported resultSep 22, 2026 | Not published | Not published |
| Terminal-Bench 2.1max effort | Not published | 88.2pass@1Reported result | Not published |
| Terminal-Bench 3.0max effort | Not published | 28.3avg@3Reported result | Not published |
| DeepSWE 1.1max effort; 6h timeout; 400K context | Not published | 66.9resolvedReported result | Not published |
| NL2Repomax effort | Not published | 58scoreReported result | Not published |
| ProgramBenchmax effort | Not published | 19almost solvedReported result | Not published |
| FrontierSWEmax effort | Not published | 78.1dominance scoreReported resultAug 14, 2026 | Not published |
| SWE-Marathon 1.1max effort; modified anti-cheat checks | Not published | 42.5scoreReported result | Not published |
| PostTrainBenchmax effort; 3 runs; modified external-API checks | Not published | 39.8weighted averageReported result | Not published |
| CyberGymmax effort | Not published | 84.5pass@1Reported result | Not published |
| ExploitGym · 869 tasksmax effort; 2h rescaled timeout | Not published | 105tasks solvedReported result | Not published |
| ExploitGym · 869 tasksmax effort; 6h rescaled timeout | Not published | 130tasks solvedReported result | Not published |
| ExploitBenchmax effort; union over 3 revisions | Not published | 54.4average coverageReported result | Not published |
| Toolathlon-Verifiedmax effort | Not published | 73pass@1Reported result | Not published |
| AutomationBench 1.0.6max effort | Not published | 48.2pass@1Reported result | Not published |
| Agents' Last Exammax effort; CLI | Not published | 28.5scoreReported result | Not published |
| Humanity's Last Exammax effort; with tools | Not published | 62.5accuracyReported result | Not published |
| GDPval-AA 2max effort | Not published | 1769EloReported result | Not published |
| Terminal-Bench 2.1max | Not published | Not published | 82.7pass@1Reported result |
| NL2Repomax effort | Not published | Not published | 54.2resolve rateReported resultJul 31, 2026 |
| CyberGymmax effort | Not published | Not published | 76.7scoreReported resultJul 31, 2026 |
| DeepSWEmax effort | Not published | Not published | 54.4resolve rateReported resultJul 31, 2026 |
| Toolathlon-Verifiedmax effort | Not published | Not published | 70.3scoreReported resultJul 31, 2026 |
| Agents' Last Exammax effort | Not published | Not published | 25.2scoreReported resultJul 31, 2026 |
| AutomationBench · publicmax effort | Not published | Not published | 25.1success rateReported resultJul 31, 2026 |
| DSBench-FullStack · internalmax effort | Not published | Not published | 68.7scoreReported resultJul 31, 2026 |
| DSBench-Hard · internalmax effort | Not published | Not published | 59.6scoreReported resultJul 31, 2026 |
| Price per million tokens | |||
| Input | $0.10 (best) | $1.40 | $0.14 |
| Output | $0.50 | $4.40 | $0.30 (best) |
| Cached input | $0.01 (best) | $0.26 | Not published |
| Blended (3:1) | $0.20 | $2.15 | $0.18 (best) |
| Long-context rate | Over 272K: $0.20 / $0.75 | Same rate | Same rate |
| Price source | Official OpenAI API | Official Z.AI API | Median of 65 providers |
| Limits | |||
| Context window | 1,050,000 tokens (best) | 1,000,000 tokens | 1,000,000 tokens |
| Max input | 922,000 tokens | Not published | Not published |
| Max output | 128,000 tokens | 131,072 tokens | 384,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh · max | Yeslow · high · max | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Not published |
| File attachments | Yes | No | No |
| Temperature control | Yes | Yes | Yes |
| Reasoning control | effort | effort | always |
| Availability | |||
| Weights | Proprietary | Open | OpenMIT |
| API model ID | gpt-6-luna | glm-5.3 | Not published |
| API providers | 49 | 123 (best) | 66 |
| Released | Sep 22, 2026 | Aug 14, 2026 | Jul 31, 2026 |
| Knowledge cutoff | May 18, 2026 | Not published | May 2025 |
| Publisher documentation | Publisher documentation | Publisher documentation · Model weights | Model weights |
| Source metadata updated | Sep 22, 2026 | Aug 14, 2026 | Jul 31, 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.
GPT-6 Luna$2.00
GLM-5.3$22.80
DeepSeek V4 Flash 0731$2.00
Which should you choose?
Which is better: GPT-6 Luna, GLM-5.3 or DeepSeek V4 Flash 0731?
It is close. Our weighted score puts them within a point (GPT-6 Luna 80/100, DeepSeek V4 Flash 0731 80/100, GLM-5.3 67/100), so choose by what matters most for your work: GLM-5.3 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (GLM-5.3 81/100, GPT-6 Luna 81/100, DeepSeek V4 Flash 0731 79/100), so choose by what matters most for your work: GLM-5.3 for raw capability, DeepSeek V4 Flash 0731 on price and GPT-6 Luna for long inputs. The score weighs capability 83%, context window 17%.
Which is cheaper, GPT-6 Luna, GLM-5.3 or DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper at $0.14 input / $0.30 output per million tokens (median across 65 API providers). GPT-6 Luna costs $0.10 input / $0.50 output per million tokens (official OpenAI 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 $0.18 per million tokens for DeepSeek V4 Flash 0731 versus $0.20 for GPT-6 Luna (1.1× as much) and $2.15 for GLM-5.3 (12× as much).
Which scores higher on benchmarks?
GLM-5.3 scores higher on the Capabilities Index (ECI): GLM-5.3 157.1 (#34 of 159), GPT-6 Luna 156.5 (#38 of 159) and DeepSeek V4 Flash 0731 154.4 (#53 of 159). The confidence ranges of the top two overlap (155.0–159.4 vs 154.6–158.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek V4 Flash 0731 91.0%, GLM-5.3 90.9%, GPT-6 Luna 90.5%; FrontierMath Tiers 1–3 — GPT-6 Luna 79.0%, GLM-5.3 68.8%, DeepSeek V4 Flash 0731 57.5%; OTIS Mock AIME 2024–2025 — GPT-6 Luna 98.9%, DeepSeek V4 Flash 0731 94.4%, GLM-5.3 91.1%; SimpleQA Verified — GPT-6 Luna 41.4%, GLM-5.3 41.0%, DeepSeek V4 Flash 0731 33.6%.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-6 Luna, GLM-5.3 and DeepSeek V4 Flash 0731 yet, so there is no like-for-like coding score. On overall capability, GLM-5.3 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 has the largest context window at 1,050,000 tokens, against 1,000,000 for GLM-5.3 and 1,000,000 for DeepSeek V4 Flash 0731. Maximum output per response: GPT-6 Luna up to 128,000, GLM-5.3 up to 131,072, DeepSeek V4 Flash 0731 up to 384,000 tokens.
Which can read images, PDFs, audio or video?
GPT-6 Luna accepts text, images and PDFs; GLM-5.3 accepts text; DeepSeek V4 Flash 0731 accepts text. GPT-6 Luna handles the widest range of inputs.
Are any of these open source?
GLM-5.3 and DeepSeek V4 Flash 0731 publishes its weights (MIT) and can be self-hosted; GPT-6 Luna is proprietary.
Which is newer?
GPT-6 Luna is the newest, released Sep 22, 2026. GLM-5.3 came out Aug 14, 2026; DeepSeek V4 Flash 0731 came out Jul 31, 2026. Knowledge cutoff: GPT-6 Luna May 18, 2026, DeepSeek V4 Flash 0731 May 2025.
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.