Model comparison
DeepSeek V4-Flash vs Gemini 3.5 Flash
DeepSeek against Google, compared on context, price, and verified benchmark results.
Catalog record checked August 18, 2026; individual provider fields may change.
DeepSeek
DeepSeek V4-Flash
Budget · Open weights
Gemini 3.5 Flash
Budget
| Specification | DeepSeek V4-Flash | Gemini 3.5 Flash |
|---|---|---|
| Provider | DeepSeek | |
| Tier | Budget | Budget |
| Context window | 1M | Winner: 1.05M |
| Max output | Winner: 384K | 66K |
| Input / 1M tokens | Not verified | $1.50 |
| Output / 1M tokens | Not verified | $9 |
| Weights | Open | Closed |
| Parameters | 284B total / 13B active (MoE) | Not disclosed |
| Reasoning levels | low, high, max | Not verified |
| Modalities | text | text, image, video, audio, pdf |
| Released | July 31, 2026 | May 19, 2026 |
| Artificial Analysis Intelligence Index [max] (2026-08-14) | 52 | Not verified |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Pricing tiers: DeepSeek V4-Flash: No single standard-tier rate after 2026-08-16 16:00 UTC. Official peak/off-peak (cache miss / output): off-peak $0.22/$0.66, peak $0.44/$1.32. Peak hours are 01:00–04:00 and 06:00–10:00 UTC. Expired intro $0.14/$0.28 is not shown as the list price. · Gemini 3.5 Flash: Google Gemini API standard paid tier is $1.50 input / $9 output per million tokens (agent verified 2026-08-18, https://ai.google.dev/gemini-api/docs/pricing). GA/stable API id `gemini-3.5-flash` (powers `gemini-flash-latest`). Token limits and modalities are from Google’s model card.
DeepSeek V4-Flash
Open-weight price-performance pick: MIT weights, 1M context, and API rates far below closed budget tiers.
Best for
- Cost-sensitive hosted agents
- High-volume coding assist
- Open-weight deployments with cluster VRAM
Watch out
Hosted billing is peak/off-peak (see pricing note), not a flat intro rate. Self-hosting the ~284B MoE still needs roughly 90–170GB+ class VRAM depending on quant — not a laptop budget build. DeepSWE snapshot also uses the shared mini-swe-agent harness — verify cost, effort, and serving conditions before treating the result as a forecast.
Gemini 3.5 Flash
Google’s generally available Gemini 3.5 Flash tier: 1M context, thinking-enabled, and the stable alias behind `gemini-flash-latest`. Distinct from Flash-Lite (cheaper throughput) and from 3.6/3.7 Flash (newer workhorses).
Best for
- Stable Google Flash alias
- Agent loops that must pin a GA id
- Multimodal volume when 3.7 is not required
Watch out
Do not treat this as Flash-Lite or as 3.7 Flash. Standard paid list is $1.50/$9; DeepSWE 1.1 high-effort is 36.1% at $3.45/task. Model card latest update: May 2026.
Benchmark
DeepSWE 1.1 in context
Both models shown against the wider field, with cost per completed task alongside the score.
Local leader
Claude Opus 5 [max]
74%
Rows shown
24
Highest published reasoning effort per model (not best Pass@1)
Snapshot date
2026-08-13
Mirrored from deepswe.datacurve.ai
Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 [max] | 74% | $11.84 | 118k | 99 |
| 2 | GPT-5.6 Sol [max] | 73% | $8.39 | 60k | 61 |
| 3 | Claude Fable 5 [max] | 70% | $21.63 | 119k | 88 |
| 4 | GPT-5.6 Terra [max] | 70% | $4.95 | 72k | 76 |
| 5 | Kimi K3 [max] | 69% | $4.65 | 82k | 98 |
| 6 | GPT-5.6 Luna [max] | 67% | $3.03 | 73k | 102 |
| 7 | GPT-5.5 [xhigh] | 67% | $7.23 | 46k | 82 |
| 8 | Grok 4.6 [xhigh] | 67% | $5.50 | 71k | 87 |
| 9 | Gemini 3.7 Flash [high] | 65% | $2.18 | 107k | 125 |
| 10 | DeepSeek V4-Pro [max] | 63% | $0.24 | 106k | 155 |
| 11 | Claude Opus 4.8 [max] | 59% | $13.22 | 135k | 120 |
| 12 | Qwen3.8-Max [xhigh] | 58% | $3.73 | 95k | 111 |
| 13 | Muse Spark 1.2 [xhigh] | 55% | $3.70 | 99k | 101 |
| 14 | Claude Sonnet 5 [max] | 54% | $26.40 | 214k | 268 |
| 15 | Grok 4.5 [high] | 54% | $2.42 | 36k | 61 |
| 16 | DeepSeek V4-Flash [max] | 53% | $0.10 | 108k | 153 |
| 17 | Muse Spark 1.1 [xhigh] | 53% | $2.36 | 74k | 96 |
| 18 | GPT-5.4 [xhigh] | 52% | $5.65 | 71k | 70 |
| 19 | Gemini 3.6 Flash [high] | 47% | $4.42 | 96k | 117 |
| 20 | GLM 5.2 [max] | 44% | $3.92 | 78k | 129 |
| 21 | Gemini 3.5 Flash [high] | 36% | $3.45 | 76k | 105 |
| 22 | Kimi K2.7 Code | 31% | $2.82 | 59k | 149 |
| 23 | Claude Sonnet 4.6 [high] | 30% | $5.52 | 76k | 134 |
| 24 | Gemini 3.1 Pro [high] | 12% | $2.14 | 28k | 76 |
DeepSWE “Best” picks the highest published reasoning effort per model (not the highest pass rate). Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
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 pickerCommon questions
DeepSeek V4-Flash vs Gemini 3.5 Flash
Answered from the verified figures on this page rather than general guidance.
Which has the larger context window, DeepSeek V4-Flash or Gemini 3.5 Flash?
Gemini 3.5 Flash accepts 1.05M tokens against 1M for DeepSeek V4-Flash. This only matters if you routinely send very long documents or large codebases.
Should I use DeepSeek V4-Flash or Gemini 3.5 Flash?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. DeepSeek V4-Flash suits cost-sensitive hosted agents; Gemini 3.5 Flash suits stable google flash alias.
Can I self-host DeepSeek V4-Flash or Gemini 3.5 Flash?
DeepSeek V4-Flash publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. Gemini 3.5 Flash is a closed model whose supported access paths are controlled by its provider.
Next step
Choosing between them
Tier and workload decide this more reliably than a leaderboard position does.
If both sit in the same tier, the decision usually comes down to context window and output price rather than headline capability — output tokens dominate real bills.
If one is a step up within the same provider, the useful question is whether your hardest task actually fails on the cheaper tier. Most production volume — classification, extraction, summarization — does not.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Muse Code, or Lovable? Compare agentic harnesses · Latest releases.