DeepSeek V4 Pro 0813 vs GPT-5.6 Luna vs Gemini 3.6 Flash
GPT-5.6 Luna comes out ahead, 78 to 73 and 68 on our weighted score, and it is the cheaper option too.
DeepSeekDeepSeek V4 Pro 0813
68/100- ECI155.4
- Price$0.66 / $1.98
- Context1M
- Our pick
OpenAIGPT-5.6 Luna
78/100- ECI156.5
- Price$0.20 / $1.20
- Context1.05M
GoogleGemini 3.6 Flash
73/100- ECI154.3
- Price$0.75 / $3.75
- Context1.05M
GPT-5.6 Luna is our pick
GPT-5.6 Luna is the better all-round choice, scoring 78/100 against Gemini 3.6 Flash (73) and DeepSeek V4 Pro 0813 (68). It leads on price. Gemini 3.6 Flash wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.6 LunaCapabilities Index (ECI): GPT-5.6 Luna 156.5 · DeepSeek V4 Pro 0813 155.4 · Gemini 3.6 Flash 154.3
- Lowest priceGPT-5.6 LunaGPT-5.6 Luna $0.45 · DeepSeek V4 Pro 0813 $0.99 · Gemini 3.6 Flash $1.50 per 1M tokens (3:1 blend)
- Longest contextGPT-5.6 Luna and Gemini 3.6 FlashGPT-5.6 Luna 1,050,000 · Gemini 3.6 Flash 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 tokens
- Widest inputsGemini 3.6 FlashDeepSeek V4 Pro 0813: Text · GPT-5.6 Luna: Text, Images, PDFs · Gemini 3.6 Flash: Text, Images, PDFs, Audio, Video
- Self-hostingDeepSeek V4 Pro 0813Publishes downloadable weights (MIT)
| Measure | Weight | DeepSeek V4 Pro 0813 | GPT-5.6 Luna | Gemini 3.6 Flash |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 85 | 86 | 84 |
| Price | 25% | 50 | 66 | 42 |
| Inputs & features | 15% | 45 | 80 | 100 |
| Context window | 10% | 60 | 61 | 61 |
| Overall | 100% | 68/100 | 78/100 | 73/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek V4 Pro 0813DeepSeek | GPT-5.6 LunaOpenAI | Gemini 3.6 FlashGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 155.4 | 156.5 (best) | 154.3 |
| ECI rank | #26 of 148 | #21 of 148 (best) | #34 of 148 |
| GPQA DiamondGraduate-level science questions | 91.7% | 91.6% | 94.1% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 64.6% | 82.1% (best) | 59.0% |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.6% (best) | 98.3% | 94.2% |
| SimpleQA VerifiedShort factual questions | 52.9% | 41.0% | 66.2% (best) |
| Price per million tokens | |||
| Input | $0.66 | $0.20 (best) | $0.75 |
| Output | $1.98 | $1.20 (best) | $3.75 |
| Cached input | $0.022 | $0.02 (best) | $0.075 |
| Blended (3:1) | $0.99 | $0.45 (best) | $1.50 |
| Long-context rate | Same rate | Over 272K: $0.40 / $1.80 | Same rate |
| Price source | Official DeepSeek API | Official OpenAI API | Official Google API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,050,000 tokens (best) | 1,048,576 tokens |
| Max output | 384,000 tokens (best) | 128,000 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yeslow · high · max | Yeslow · medium · high · xhigh · max | Yesminimal · low · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | OpenMIT | Proprietary | Proprietary |
| API model ID | deepseek-v4-pro | gpt-5.6-luna | gemini-3.6-flash |
| API providers | 37 | 38 (best) | 25 |
| Released | Aug 12, 2026 | Jul 9, 2026 | Jul 21, 2026 |
| Knowledge cutoff | — | Feb 16, 2026 | Mar 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 Pro 0813$10.56
- GPT-5.6 Luna$4.40
- Gemini 3.6 Flash$15.00
Which should you choose?
Which is better: DeepSeek V4 Pro 0813, GPT-5.6 Luna or Gemini 3.6 Flash?
GPT-5.6 Luna is the better all-round choice, scoring 78/100 against Gemini 3.6 Flash (73) and DeepSeek V4 Pro 0813 (68). It leads on price. Gemini 3.6 Flash wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek V4 Pro 0813, GPT-5.6 Luna or Gemini 3.6 Flash?
GPT-5.6 Luna is cheaper at $0.20 input / $1.20 output per million tokens (official OpenAI API price). DeepSeek V4 Pro 0813 costs $0.66 input / $1.98 output per million tokens (official DeepSeek API price); Gemini 3.6 Flash costs $0.75 input / $3.75 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for GPT-5.6 Luna versus $0.99 for DeepSeek V4 Pro 0813 (2.2× as much) and $1.50 for Gemini 3.6 Flash (3.3× as much).
Which scores higher on benchmarks?
GPT-5.6 Luna scores higher on the Capabilities Index (ECI): GPT-5.6 Luna 156.5 (#21 of 148), DeepSeek V4 Pro 0813 155.4 (#26 of 148) and Gemini 3.6 Flash 154.3 (#34 of 148). The confidence ranges of the top two overlap (154.1–158.6 vs 153.7–157.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.6 Flash 94.1%, DeepSeek V4 Pro 0813 91.7%, GPT-5.6 Luna 91.6%; FrontierMath Tiers 1–3 — GPT-5.6 Luna 82.1%, DeepSeek V4 Pro 0813 64.6%, Gemini 3.6 Flash 59.0%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 0813 98.6%, GPT-5.6 Luna 98.3%, Gemini 3.6 Flash 94.2%; SimpleQA Verified — Gemini 3.6 Flash 66.2%, DeepSeek V4 Pro 0813 52.9%, GPT-5.6 Luna 41.0%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Pro 0813, GPT-5.6 Luna and Gemini 3.6 Flash yet, so there is no like-for-like coding score. On overall capability, GPT-5.6 Luna 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 Gemini 3.6 Flash have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4 Pro 0813. Maximum output per response: DeepSeek V4 Pro 0813 up to 384,000, GPT-5.6 Luna up to 128,000, Gemini 3.6 Flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro 0813 accepts text; GPT-5.6 Luna accepts text, images and PDFs; Gemini 3.6 Flash accepts text, images, PDFs, audio and video. Gemini 3.6 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro 0813 publishes its weights (MIT) and can be self-hosted; GPT-5.6 Luna and Gemini 3.6 Flash is proprietary.
Which is newer?
DeepSeek V4 Pro 0813 is the newest, released Aug 12, 2026. Gemini 3.6 Flash came out Jul 21, 2026; GPT-5.6 Luna came out Jul 9, 2026. Knowledge cutoff: GPT-5.6 Luna Feb 16, 2026, Gemini 3.6 Flash Mar 2026.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.
Related comparisons
- DeepSeek V4 Pro 0813 vs Muse Spark 1.2Meta · ECI 155.0
- DeepSeek V4 Pro 0813 vs GLM-5.3Z.ai (Zhipu) · ECI 155.8
- GPT-5.6 Luna vs DeepSeek V4.1 FlashDeepSeek · ECI 155.0
- GPT-5.6 Luna vs Gemini 3.8 FlashGoogle · ECI 156.9
- GPT-5.6 Luna vs GLM-5.3-FlashZ.ai (Zhipu) · ECI 151.9
- GPT-5.6 Luna vs Inkling SmallThinking Machines · ECI 150.2
