Model comparison
DeepSeek V4 Flash vs GPT-5.6 Luna
DeepSeek against OpenAI, compared on context, price, and attributed benchmark results.
Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: Insufficient data — see receipts below
DeepSeek
DeepSeek V4 Flash
Balanced · Open weights
OpenAI
GPT-5.6 Luna
Budget
| Specification | DeepSeek V4 Flash | GPT-5.6 Luna |
|---|---|---|
| Provider | ||
| Provider | DeepSeek | OpenAI |
| Tier | ||
| Tier | Balanced | Budget |
| Context window | ||
| Context window | 1M | Winner: 1.05M |
| Max output | ||
| Max output | Not verifiedUnverified | 128K |
| Input / 1M tokens | ||
| Input / 1M tokens | Not verifiedUnverified | $0.20 |
| Output / 1M tokens | ||
| Output / 1M tokens | Not verifiedUnverified | $1.20 |
| Weights | ||
| Weights | Open | Closed |
| Parameters | ||
| Parameters | 284B total / 13B active (MoE) | Not verifiedUnverified |
| Reasoning levels | ||
| Reasoning levels | low, high, max | none, low, medium, high, xhigh, max |
| Modalities | ||
| Modalities | text | text, image |
| License | ||
| License | MIT | Not verifiedUnverified |
| API model id | ||
| API model id | deepseek-v4-flash | gpt-5.6-luna |
| Released | ||
| Released | April 24, 2026 | July 9, 2026 |
| SWE-bench Verified · source date DeepSeek V4 Flash: 2026-04-24 | ||
| SWE-bench Verified · source date DeepSeek V4 Flash: 2026-04-24 | 79 | Not verifiedUnverified |
| GPQA Diamond · source date DeepSeek V4 Flash: 2026-04-24 | ||
| GPQA Diamond · source date DeepSeek V4 Flash: 2026-04-24 | 88.1 | Not verifiedUnverified |
| Humanity's Last Exam · source date DeepSeek V4 Flash: 2026-04-24 | ||
| Humanity's Last Exam · source date DeepSeek V4 Flash: 2026-04-24 | 45.1 | Not verifiedUnverified |
| MMLU-Pro · source date DeepSeek V4 Flash: 2026-04-24 | ||
| MMLU-Pro · source date DeepSeek V4 Flash: 2026-04-24 | 86.2 | Not verifiedUnverified |
| Terminal-Bench 2.1 · source date GPT-5.6 Luna: 2026-07-09 | ||
| Terminal-Bench 2.1 · source date GPT-5.6 Luna: 2026-07-09 | Not verifiedUnverified | 84.7 |
| LiveBench · source date GPT-5.6 Luna: 2026-09-05 | ||
| LiveBench · source date GPT-5.6 Luna: 2026-09-05 | Not verifiedUnverified | 73.6 |
Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
Where each score comes from, and how far it can be compared across models.
- Source date2026-09-05LiveBench official leaderboard (benchmark-owned), max effort
Contamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes.
Comparable with caveatCompare only observations confirmed to use the same exact question-set version. Date proximity (including within one month) does not establish identical questions; when the version is unavailable, treat the scores as unaligned.
- Source date2026-07-09OpenAI GPT-5.6 launch table (vendor-reported; effort and experiment date unspecified) (Vendor launch table; complete common run settings unverified)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.
- Source date2026-04-24DeepSeek family HF model card (vendor, Think Max, exact match)
Broad knowledge across 14 domains with harder, reasoning-focused multiple-choice questions.
Comparable with caveatFrontier models cluster in the high 80s–90s; near-ceiling differences are weak evidence. CoT vs direct answering must match.
- Source date2026-04-24DeepSeek family HF model card (vendor, Think Max, with tools; 34.8 no tools)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
- Source date2026-04-24DeepSeek family HF model card (vendor, Think Max, pass@1)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
- Source date2026-04-24DeepSeek original family HF model card (vendor, Think Max; historical April checkpoint, not the 0731 refresh)
Real GitHub issue resolution: does the model's patch pass the hidden tests.
Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
Pricing tiers
DeepSeek V4 Flash: Retired 2026-09-10 — no longer sold. Historical checkpoint tariffs are not verified here. The legacy deepseek-v4-flash ID temporarily routes to V4.1-Flash at $0.30/$1.20 peak or $0.15/$0.60 off-peak. MIT weights remain. A current 384K API output limit belongs to the routed V4.1-Flash; the original checkpoint's hard output cap is not verified.
GPT-5.6 Luna: Launch $1/$6, reduced to $0.20/$1.20 on July 30. Above 272K input the full request bills $0.40/$1.80. Cached input $0.02; cache writes $0.25 at short context. Batch $0.10/$0.60 at short context. Regional/FedRAMP processing adds 10% where eligible.
DeepSeek V4 Flash
DeepSeek V4 Flash was the efficient open-weight (MIT) sibling of V4 Pro — retired from DeepSeek's API on 2026-09-10 and replaced by V4.1-Flash.
Best for
- Open-weight deployments
- Cost-sensitive inference
- High-volume serving
Watch out
Retired from the first-party API: the legacy ID reaches V4.1-Flash, not these original weights. MIT weights remain for self-hosting. Do not transfer the current alias's output cap or vision capabilities to the original text-only checkpoint.
GPT-5.6 Luna
OpenAI’s GPT-5.6 budget tier, succeeded by GPT-6 Luna on September 22. The newer model halves input pricing ($0.20→$0.10) and lowers output pricing from $1.20 to $0.50.
Best for
- Classification
- High-volume chat
- Latency-sensitive pipelines
Watch out
Superseded by GPT-6 Luna and still listed in the API. Historical index captures are not current evidence of equal quality; the successor has lower Standard input and output prices.
When the cheaper one wins
One of these rows is missing a verified output price, so this page will not name a cheaper winner. Run the model picker against the actual job instead of guessing.
Run the model pickerEvidence confidence: Insufficient data
How strong and complete the evidence behind this comparison is — not a prediction of which model is better. Hard limitations apply: missing pricing; evidence too sparse.
- Pricing incomplete — No verified token pricing for DeepSeek V4 Flash.
- 3/5 core specs verified on both sides — Not published for at least one side: max output, parameter count.
- No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
- Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- DeepSeek V4 Flash: Whole-profile primary source check October 1 (accessed 2026-10-01)
- DeepSeek V4 Flash: Whole-profile primary source check October 1 (accessed 2026-10-01)
- DeepSeek V4 Flash: DeepSeek — V4 news (accessed 2026-08-29)
- DeepSeek V4 Flash: DeepSeek API pricing (accessed 2026-08-29)
- DeepSeek V4 Flash: DeepSeek — V4.1-Flash release (V4-Flash retired) (accessed 2026-09-26)
- DeepSeek V4 Flash: DeepSeek API pricing (legacy id billed at V4.1-Flash rates) (accessed 2026-09-26)
- GPT-5.6 Luna: OpenAI model card — whole-profile source check October 1 (accessed 2026-10-01)
- GPT-5.6 Luna: OpenAI current API pricing and processing tiers (accessed 2026-10-01)
- GPT-5.6 Luna: OpenAI — GPT-5.6 (accessed 2026-08-29)
- GPT-5.6 Luna: OpenAI API pricing (gpt-5.6-luna $0.20/$1.20) (accessed 2026-08-29)
- GPT-5.6 Luna: OpenAI — Introducing GPT-6 Sol and Luna (GPT-5.6 Luna successor) (accessed 2026-09-26)
Related comparisons
- Amazon Nova 2 Lite vs DeepSeek V4 Flash
- Amazon Nova 2 Pro vs DeepSeek V4 Flash
- Base 1 vs DeepSeek V4 Flash
- Claude Haiku 4.5 vs GPT-5.6 Luna
- Claude Opus 5 vs DeepSeek V4 Flash
- Claude Opus 5 vs GPT-5.6 Luna
Diving deeper on one model? DeepSeek V4 Flash · GPT-5.6 Luna
Common questions
DeepSeek V4 Flash vs GPT-5.6 Luna
Answered from the verified figures on this page rather than general guidance.
Which has the larger context window, DeepSeek V4 Flash or GPT-5.6 Luna?
Do DeepSeek V4 Flash and GPT-5.6 Luna support the same reasoning levels?
Should I use DeepSeek V4 Flash or GPT-5.6 Luna?
Can I self-host DeepSeek V4 Flash or GPT-5.6 Luna?
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Context: GPT-5.6 Luna takes 1.05M against 1M for DeepSeek V4 Flash — only decisive if your prompts approach the smaller window.
- Deployment: DeepSeek V4 Flash publishes weights you can self-host; the other is API-only.
- Positioning: DeepSeek V4 Flash sits in the balanced tier, GPT-5.6 Luna in the budget tier. Compare accuracy, reliability, latency, and cost on representative tasks before choosing.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.