Compare / Claude Haiku 5.5 vs DeepSeek-V4-Pro (0423)
Claude Haiku 5.5 vs DeepSeek-V4-Pro (0423)
Which is cheaper, which is more capable, and which does better at each kind of work, from 30 results on 3 sources that measured both models.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
Claude Haiku 5.5 or DeepSeek-V4-Pro (0423)? The short answer
Pick Claude Haiku 5.5: it scores higher (Spring Prompt overall 44 against 33) and costs less.
- Spring Prompt overall: Claude Haiku 5.5 44, DeepSeek-V4-Pro (0423) 33 (out of 100; how the score works).
- Claude Haiku 5.5 is cheaper to run: $0.009 against $0.046 per deck on DeckBench (5.1 times less).
- Claude Haiku 5.5 scores higher on the Artificial Analysis Intelligence Index: 43.4 against 30.4.
- Claude Haiku 5.5 is newer: released 7 Oct 2026, against 24 Apr 2026 for DeepSeek-V4-Pro (0423).
- On our own benchmarks, on the results both models have: Claude Haiku 5.5 does better for decks from an analysis; DeepSeek-V4-Pro (0423) for marketing planning.
- On third-party benchmarks, on the results both models have: Claude Haiku 5.5 does better for agents and tool use and reasoning and knowledge.
At a glance
| Claude Haiku 5.5 | DeepSeek-V4-Pro (0423) | |
|---|---|---|
| Price per million tokens | $0.10 in · $0.50 out | $1.42 in · $2.83 out |
| Blended (3 in : 1 out) | $0.20 | $1.77 |
| Cheapest host, blended | – | $1.19 (StreamLake, FP8) |
| Cost per deck (DeckBench) | $0.009 | $0.046 |
| Intelligence Index | 43.4 | 30.4 |
| Spring Prompt overall | 44 | 33 |
| Output speed, tokens a second | 235 | – |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Released | 7 Oct 2026 (newer) | 24 Apr 2026 |
| Weights | Closed | Open |
| Developer based in | the US | China |
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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Claude Haiku 5.5 | DeepSeek-V4-Pro (0423) |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 11 of 20 | not measured |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | 10 of 19 | 18 of 19 |
| User surveysPlanning a user survey and reading its results without being misled | 3 of 8 | not measured |
| Marketing planningPlanning a year of ad spend without overspending | 17 of 19 | 13 of 19 |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 20 of 164 | 86 of 164 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 19 of 198 | 45 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | not measured | 30 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 57 of 152 |
| Speed under pressureGood decisions against a real clock (fast chess) | 15 of 22 | 23 of 23 |
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. 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 | Claude Haiku 5.5 | DeepSeek-V4-Pro (0423) |
|---|---|---|
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better | $0.0091 | $0.0465 |
| 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. | 1,130 | 613 |
| Accurate decks% of tasks, higher is better | 33.3% | 0.0% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better | 24.1 | 28.3 |
| Audience scorescore out of 100, higher is better | 48.4 | 44.8 |
| Business scorescore out of 100, higher is better | 13.5 | 23.8 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 43.4max reasoning | 30.4max reasoning |
| Humanity's Last Exam% of questions, higher is better | 44.4%max reasoning | 37.5%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better | 32.8%max reasoning | 14.6%max reasoning |
Show all 30 results (21 more)
| Measure | Claude Haiku 5.5 | DeepSeek-V4-Pro (0423) |
|---|---|---|
| DeckBench measured by Spring Prompt · 13 results | ||
| Caveat dropped% of tasks, lower is better | 16.7% | 16.7% |
| Clean layout% of tasks, higher is better | 66.7% | 33.3% |
| Design quality% of the maximum, higher is better | 61.1% | 40.9% |
| Draft figure quoted% of tasks, lower is better | 33.3% | 33.3% |
| Findings missing% of tasks, lower is better | 16.7% | 16.7% |
| 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. | 50.0% | 17.7% |
| Layout defects% of tasks, lower is better | 33.3% | 66.7% |
| Misleading metric used% of tasks, lower is better | 16.7% | 0.0% |
| Presentable decks% of tasks, higher is better | 33.3% | 0.0% |
| Recommendation late or wrong% of tasks, lower is better | 33.3% | 66.7% |
| Slides needing work% of tasks, lower is better | 16.7% | 83.3% |
| Unsupported claims% of tasks, lower is better | 33.3% | 66.7% |
| Unsupported numbers% of tasks, lower is better | 16.7% | 0.0% |
| ROASBench measured by Spring Prompt · 6 results | ||
| Consistency scorescore out of 100, higher is better | 10.6 | 9.1 |
| Contribution profitsimulated US dollars, higher is better | $32,146 | $301,289 |
| Cost of a runUS dollars, lower is better | $0.0313 | $0.20 |
| Months over budgetmonths of 12, lower is better | 0 | 0 |
| Planning scorescore out of 100, higher is better | 54.8 | 54.0 |
| Return on ad spendprofit per $1 spent, higher is better | $0.03 | $0.26 |
| Artificial Analysis reported by Artificial Analysis · 2 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 82.7%max reasoning | 74.7%max reasoning |
| SciCode% of problems, higher is better | 55.0%max reasoning | 50.8%max reasoning |
Quick answers
Is Claude Haiku 5.5 better than DeepSeek-V4-Pro (0423)?
Pick Claude Haiku 5.5: it scores higher (Spring Prompt overall 44 against 33) and costs less.
Which is cheaper, Claude Haiku 5.5 or DeepSeek-V4-Pro (0423)?
Claude Haiku 5.5 is cheaper to run: $0.009 against $0.046 per deck on DeckBench (5.1 times less).
Run Claude Haiku 5.5 and DeepSeek-V4-Pro (0423) on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.