Compare / DeepSeek-V4-Pro (0423) vs Gemini 4 Argon
DeepSeek-V4-Pro (0423) vs Gemini 4 Argon
Which is cheaper, which is more capable, and which does better at each kind of work, from 38 results on 4 sources that measured both models.
Of the 38 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 14 October 2026 (catalogue release 2026-10-14-7d7cf32c3f6d). See also DeepSeek vs Google, every model from both labs.
DeepSeek-V4-Pro (0423) or Gemini 4 Argon? The short answer
Pick Gemini 4 Argon if quality matters most: it scores higher (Spring Prompt overall 75 against 31). Pick DeepSeek-V4-Pro (0423) if cost matters more: it costs 2.5 times less per deck on DeckBench.
- Spring Prompt overall: DeepSeek-V4-Pro (0423) 31, Gemini 4 Argon 75 (out of 100; how the score works).
- DeepSeek-V4-Pro (0423) is cheaper to run: $0.046 against $0.11 per deck on DeckBench (2.5 times less).
- Gemini 4 Argon scores higher on the Artificial Analysis Intelligence Index: 52.6 against 30.4.
- Gemini 4 Argon is newer: released 13 Oct 2026, against 24 Apr 2026 for DeepSeek-V4-Pro (0423).
- On our own benchmarks, on the results both models have: Gemini 4 Argon does better for decks from an analysis and marketing planning.
- On third-party benchmarks, on the results both models have: Gemini 4 Argon does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| DeepSeek-V4-Pro (0423) | Gemini 4 Argon | |
|---|---|---|
| Price per million tokens | $1.42 in · $2.83 out | $2.00 in · $10.00 out |
| Blended (3 in : 1 out) | $1.77 | $4.00 |
| Cheapest host, blended | $1.19 (StreamLake, FP8) | – |
| Cost per deck (DeckBench) | $0.046 | $0.11 |
| Intelligence Index | 30.4 | 52.6 |
| Spring Prompt overall | 31 | 75 |
| Output speed, tokens a second | – | – |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Released | 24 Apr 2026 | 13 Oct 2026 (newer) |
| Weights | Open | Closed |
| Developer based in | China | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | DeepSeek-V4-Pro (0423) | Gemini 4 Argon |
|---|---|---|
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 8 · 10 of 21 measured | $0.0465 | $0.11 |
| Deck ratingrating, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 21 · 13 of 21 measured | 564 | 998 |
| Accurate decks% of tasks, higher is better 18 · 13 of 21 measured | 0.0% | 33.3% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better 15 · 8 of 21 measured | 28.3 | 47.0 |
| Audience scorescore out of 100, higher is better 18 · 8 of 21 measured | 44.8 | 65.5 |
| Business scorescore out of 100, higher is better 15 · 8 of 21 measured | 23.8 | 43.3 |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 53 · 1 of 387 measured | 1,458 | 1,525high reasoning |
| Overall · Text factualityArena rating, higher is better 49 · 1 of 163 measured | 1,455 | 1,511high reasoning |
| Business, management and finance · TextArena rating, higher is better 52 · 1 of 380 measured | 1,460 | 1,522high reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 50 · 5 of 244 measured | 30.4max reasoning | 52.6high reasoning |
| Humanity's Last Exam% of questions, higher is better 52 · 3 of 243 measured | 37.5%max reasoning | 57.1%high reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 28 · 4 of 113 measured | 14.6%max reasoning | 57.1%high reasoning |
Show all 38 results (26 more)
| Measure | DeepSeek-V4-Pro (0423) | Gemini 4 Argon |
|---|---|---|
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 12 · 1 of 21 measured | 16.7% | 0.0% |
| Clean layout% of tasks, higher is better 13 · 13 of 21 measured | 33.3% | 33.3% |
| Design quality% of the maximum, higher is better 20 · 16 of 21 measured | 40.9% | 55.2% |
| Draft figure quoted% of tasks, lower is better 12 · 17 of 21 measured | 33.3% | 50.0% |
| Findings missing% of tasks, lower is better 16 · 1 of 21 measured | 16.7% | 0.0% |
| Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 20 · 13 of 21 measured | 21.8% | 57.0% |
| Layout defects% of tasks, lower is better 13 · 13 of 21 measured | 66.7% | 66.7% |
| Misleading metric used% of tasks, lower is better 1 · 1 of 21 measured | 0.0% | 0.0% |
| Presentable decks% of tasks, higher is better 12 · 12 of 21 measured | 0.0% | 0.0% |
| Recommendation late or wrong% of tasks, lower is better 18 · 1 of 21 measured | 66.7% | 0.0% |
| Slides needing work% of tasks, lower is better 19 · 15 of 21 measured | 83.3% | 66.7% |
| Time per deckseconds, lower is better 18 · 6 of 21 measured | 332 | 67.5 |
| Unsupported claims% of tasks, lower is better 21 · 11 of 21 measured | 66.7% | 16.7% |
| Unsupported numbers% of tasks, lower is better 1 · 1 of 21 measured | 0.0% | 0.0% |
| ROASBench measured by Spring Prompt · 6 results | ||
| Consistency scorescore out of 100, higher is better 19 · 5 of 21 measured | 9.1 | 34.7 |
| Contribution profitsimulated US dollars, higher is better 14 · 5 of 21 measured | $301,289 | $673,561 |
| Cost of a runUS dollars, lower is better 10 · 11 of 21 measured | $0.20 | $0.24 |
| Months over budgetmonths of 12, lower is better 1 · 1 of 21 measured | 0 | 0 |
| Planning scorescore out of 100, higher is better 20 · 1 of 21 measured | 54.0 | 55.4 |
| Return on ad spendprofit per $1 spent, higher is better 14 · 8 of 21 measured | $0.26 | $0.55 |
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 39 · 1 of 385 measured | 1,446 | 1,519high reasoning |
| Expert prompts · TextArena rating, higher is better 64 · 7 of 338 measured | 1,480 | 1,539high reasoning |
| Instruction following · TextArena rating, higher is better 52 · 1 of 387 measured | 1,452 | 1,528high reasoning |
| Writing, literature and language · TextArena rating, higher is better 44 · 1 of 386 measured | 1,451 | 1,522high reasoning |
| Artificial Analysis reported by Artificial Analysis · 2 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better 80 · 44 of 234 measured | 74.7%max reasoning | 79.7%high reasoning |
| SciCode% of problems, higher is better 45 · 3 of 114 measured | 50.8%max reasoning | 61.8%high reasoning |
Compare them with other models
- DeepSeek vs GoogleEvery model from both labs, best against best
- DeepSeek-V4-Pro (0423) vs Muse Spark 1.3Most intelligent at $1–3 per million tokens
- DeepSeek-V4-Pro (0423) vs Claude Opus 5.5Most intelligent available today
- Gemini 4 Argon vs Claude Opus 5.5Most intelligent at $3–10 per million tokens
- Gemini 4 Argon vs Claude Sonnet 5.5Cheapest with similar intelligence
- Gemini 4 Argon vs GPT-6 AstraJust above overall
- Gemini 4 Argon vs Muse WonderJust below overall
Quick answers
Is DeepSeek-V4-Pro (0423) better than Gemini 4 Argon?
Pick Gemini 4 Argon if quality matters most: it scores higher (Spring Prompt overall 75 against 31). Pick DeepSeek-V4-Pro (0423) if cost matters more: it costs 2.5 times less per deck on DeckBench.
Which is cheaper, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
DeepSeek-V4-Pro (0423) is cheaper to run: $0.046 against $0.11 per deck on DeckBench (2.5 times less).
Which is better for decks from an analysis, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
Gemini 4 Argon ranks 13 of 21 models on sale for turning a finished analysis into a deck you could present as it is, against 21 for DeepSeek-V4-Pro (0423).
Which is better for marketing planning, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
Gemini 4 Argon ranks 8 of 21 models on sale for planning a year of ad spend without overspending, against 15 for DeepSeek-V4-Pro (0423).
Which is better for agents and tool use, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
Gemini 4 Argon ranks 3 of 166 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 88 for DeepSeek-V4-Pro (0423).
Which is better for reasoning and knowledge, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
Gemini 4 Argon ranks 3 of 200 models on sale for hard questions across science, maths and general knowledge, against 47 for DeepSeek-V4-Pro (0423).
Which is better for writing, DeepSeek-V4-Pro (0423) or Gemini 4 Argon?
Gemini 4 Argon ranks 1 of 189 models on sale for what people prefer in blind comparisons, and judged writing quality, against 30 for DeepSeek-V4-Pro (0423).
Run DeepSeek-V4-Pro (0423) and Gemini 4 Argon on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.