AnthropicDeepSeekLLM matchup
Claude Haiku 5.5vs.DeepSeek-V4-Pro
Which one is better?
Claude Haiku 5.5 performs better than DeepSeek-V4-Pro and is cheaper: DeepSeek-V4-Pro costs 6.6 times (input) and 4 times (output) as much.
103.4
Claude Haiku 5.5
Rank 20
86.8
DeepSeek-V4-Pro
Rank 43
236
Claude Haiku 5.5
70
DeepSeek-V4-Pro
$0.20
Claude Haiku 5.5
$0.99
DeepSeek-V4-Pro
77
Claude Haiku 5.5
Rank 3 of 875
58
DeepSeek-V4-Pro
Rank 45 of 875
Above 100,000 tokens of context, Claude Haiku 5.5 costs more: $0.50 input and $2.50 output per 1M tokens.
Choose Claude Haiku 5.5 for
HealthMathematicsReasoningGeneralFinanceCodingAgentsProductivityLegal
Choose DeepSeek-V4-Pro for
No clear advantage
Where is the difference?
Strengths at a glance
Haiku 5.5DeepSeek-V4-Pro
The median of all ranked models is below 100 in every area, so it sits in the centre of the net.
CodingHaiku 5.5 ahead
Haiku 5.5106.2Rank 18
DeepSeek-V4-Pro90.4Rank 49
Median of ranked models83.7
95 % range: Haiku 5.5 102.5 to 109.9, DeepSeek-V4-Pro 85.8 to 95.0.
AreaHaiku 5.5DeepSeek-V4-Pro
The same values and verdicts as the bars below. In the top field the net starts at 100 points, the reference group average; values below sit as a hollow point in the centre. Not in the net because a model has no own value there or the data are too thin: Multimodal.
Haiku 5.5 is ahead in 8 of 9 areas, DeepSeek-V4-Pro in none.
Haiku 5.5 ahead: 8level: 1
Areas in the overall index
MathematicsHaiku 5.5 +22107.1 to 85.4
ReasoningHaiku 5.5 +21105.2 to 84.6
GeneralHaiku 5.5 +19106.4 to 87.1
CodingHaiku 5.5 +16106.2 to 90.4
AgentsHaiku 5.5 +13106.1 to 92.9
Knowledgelevel85.5 to 88.3
Specialist fields
HealthHaiku 5.5 +27108.9 to 81.8
FinanceHaiku 5.5 +18104.7 to 87.2
LegalHaiku 5.5 +1194.4 to 83.8
Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.
Show 3 more areas that do not count toward the overall index
ProductivityHaiku 5.5 +12101.8 to 89.5
Cybersecurityonly Haiku 5.5 has a score
Educationonly Haiku 5.5 has a score
Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.
Claude Haiku 5.5 vs. DeepSeek-V4-Pro at the same effort
Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.
maxHaiku 5.5 ahead
Haiku 5.5 103.4 vs. DeepSeek-V4-Pro 86.8 · Gap 13.8 · Test series 11
Overall index (max vs. max)Haiku 5.5 ahead
Haiku 5.5 103.4 vs. DeepSeek-V4-Pro 86.8
| Effort | Haiku 5.5 | DeepSeek-V4-Pro | Gap | Verdict | Test series |
|---|---|---|---|---|---|
| max | 103.4 | 86.8 | 13.8 | Haiku 5.5 ahead | 11 |
| Overall index (max vs. max) | 103.4 | 86.8 | 16.6 | Haiku 5.5 ahead |
Gap and verdict compare only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors. The single values rest on all test series of each model, so their difference can deviate from the gap.
Which model for which task?
Everyday tasks, translated from the area values above. Each row names the values it rests on.
TaskBetter choicebased on
Writing and debugging codeHaiku 5.5Coding 106.2 to 90.4
Maths and data analysisHaiku 5.5Mathematics 107.1 to 85.4, Reasoning 105.2 to 84.6
Facts and researchlevelKnowledge 85.5 to 88.3
Agents and workflowsHaiku 5.5Agents 106.1 to 92.9
Fast chat repliesHaiku 5.5236 to 70 tokens per second
Security analysisopenCybersecurity without a score for DeepSeek-V4-Pro
Many requests on a small budgetHaiku 5.5$0.20 to $0.99 per 1M tokens
Finance, legal and medical textsHaiku 5.5Finance 104.7 to 87.2, Legal 94.4 to 83.8, Health 108.9 to 81.8
See for yourself: same task, one attempt
SVG short test
One SVG task with the same fixed settings for every model, without hidden thinking.
Prompt
Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.
Claude Haiku 5.5
Unavailable in this round
DeepSeek-V4-Pro
Oct 14, 2026 · $0.0020
Test details
- Test run
- Oct 14, 2026
- Provider
- streamlake
- API model
- deepseek/deepseek-v4-pro-0813
- Output
- 963 tokens
- Reasoning
- API reports 0 reasoning tokens
- Cost of the attempt
- $0.0020
- Test round
- 43b8c5c46830
Earlier tests
Claude Haiku 5.5
Not tested yet
DeepSeek-V4-Pro
The response reached the token limit. No complete recording is available.
Oct 5, 2026 · 68 s · $0.02
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Test details
- Run date
- Oct 5, 2026
- API provider
- openrouter
- Requested API model
- deepseek/deepseek-v4-pro-0813
- Reasoning setting
- high
- Token limit including reasoning
- 8,192 tokens
- Output tokens
- 8,192 tokens
- Cost of the attempt
- $0.0163
- Response time
- 67.6 s
- API model reported in response
- deepseek/deepseek-v4-pro-0813
- Pinned endpoint
- DeepSeek | deepseek/deepseek-v4-pro-20260813
- Temperature
- Provider default
- Test protocol
- community-visual-tests-v1
- Technical checks
- Failed
Earlier attempts (3)
- Oct 2, 2026API request failedReasoning setting: high
- Oct 1, 2026API request failedReasoning setting: high
- Sep 7, 2026API request failedReasoning setting: high
Claude Haiku 5.5 and DeepSeek-V4-Pro in the overall index
Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.
Overall index (Gradually Meta-Score v4)
20 of 91 models
4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.
Claude Opus 5.5max126.1
Gemini 4 Carbonhigh125.7
Claude Fable 5.1max123.8
Claude Sonnet 5.5max122.8
Gemini 4 Argonhigh122.3
GPT-6 Astramax121.3
GPT-6.1 Solmax119.2
Muse Wonder Fullmax118.3
Claude Opus 5max117.2
Muse Wondermax113.4
Kimi K3.1 Promax112.9
Claude Fable 5max112.5
GPT-6 Solmax110.6
GPT-5.6 Solmax108.7
Muse Spark 1.3max107.4
Gemini 3.7 Flashhigh107.1
DeepSeek V4.1 Flash 1017max106.6
Gemini 3.8 Flashhigh106.5
Claude Haiku 5.5max103.4
DeepSeek-V4-Promax86.8
Claude Opus 5.5, Anthropic: 126.1 · Rank 1 · reasoning effort max
Gemini 4 Carbon, Google DeepMind: 125.7 · Rank 2 · reasoning effort high
Claude Fable 5.1, Anthropic: 123.8 · Rank 3 · reasoning effort max
Claude Sonnet 5.5, Anthropic: 122.8 · Rank 4 · reasoning effort max
Gemini 4 Argon, Google DeepMind: 122.3 · Rank 5 · reasoning effort high
GPT-6 Astra, OpenAI: 121.3 · Rank 6 · reasoning effort max
GPT-6.1 Sol, OpenAI: 119.2 · Rank 7 · reasoning effort max
Muse Wonder Full, Meta: 118.3 · Rank 8 · reasoning effort max
Claude Opus 5, Anthropic: 117.2 · Rank 9 · reasoning effort max
Muse Wonder, Meta: 113.4 · Rank 10 · reasoning effort max
Kimi K3.1 Pro, Moonshot AI: 112.9 · Rank 11 · reasoning effort max
Claude Fable 5, Anthropic: 112.5 · Rank 12 · reasoning effort max
GPT-6 Sol, OpenAI: 110.6 · Rank 13 · reasoning effort max
GPT-5.6 Sol, OpenAI: 108.7 · Rank 14 · reasoning effort max
Muse Spark 1.3, Meta: 107.4 · Rank 15 · reasoning effort max
Gemini 3.7 Flash, Google: 107.1 · Rank 16 · reasoning effort high
DeepSeek V4.1 Flash 1017, DeepSeek: 106.6 · Rank 17 · reasoning effort max
Gemini 3.8 Flash, Google: 106.5 · Rank 18 · reasoning effort high
Claude Haiku 5.5, Anthropic: 103.4 · Rank 20 · reasoning effort max
DeepSeek-V4-Pro, DeepSeek: 86.8 · Rank 43 · reasoning effort max
Claude Opus 5.5
Gemini 4 Carbon
Claude Fable 5.1
Claude Sonnet 5.5
Gemini 4 Argon
GPT-6 Astra
GPT-6.1 Sol
Muse Wonder Full
Claude Opus 5
Muse Wonder
Kimi K3.1 Pro
Claude Fable 5
GPT-6 Sol
GPT-5.6 Sol
Muse Spark 1.3
Gemini 3.7 Flash
DeepSeek V4.1 Flash 1017
Gemini 3.8 Flash
Claude Haiku 5.5
DeepSeek-V4-Pro
Popularity compared
How often the models are searched for, used and mentioned, on a scale from 0 to 100.
Claude Haiku 5.5 is more popular than DeepSeek-V4-Pro: 77 to 58 out of 100.
Over time
Weekly values from October 18, 2026 to November 5, 2026
Claude Haiku 5.5DeepSeek-V4-Pro
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | Claude Haiku 5.5 | DeepSeek-V4-Pro |
|---|---|---|
| Intelligence | ||
| Overall indexpoints, 100 = reference group average, higher is better | 103.4 | 86.8 |
| Rank | Rank 20 of 91 | Rank 43 of 91 |
| Price per 1M tokens | ||
| Inputwhat you send | $0.10above 100,000 tokens: $0.50 | $0.66 |
| Outputwhat the model writes | $0.50above 100,000 tokens: $2.50 | $1.98 |
| Speed | ||
| Tokens per second | 236 | 70 |
| Popularity | ||
| Popularitysearch, usage and mentions, 0 to 100 | 77Rank 3 of 875 | 58Rank 45 of 875 |
| Technical | ||
| Context windowhow much text the model reads at once | 1 M tokens≈ 1,500 A4 pages | 1 M tokens≈ 1,500 A4 pages |
| Knowledge cutoff | June 2026 | n/a |
| Released | Oct 7, 2026 | Apr 24, 2026 |
| Availability | Active | Active |
| Open weights | no | yes |
- DeepSeek-V4-Pro: At peak times (Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC) the price is $1.32 input and $3.96 output per 1M tokens. The table shows the off-peak price.
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Is there a better choice?
Cheaper than Haiku 5.5MiMo V2.6 Flash
Overall index 98.3, rank 31. $0.14 input and $0.28 output per 1M tokens.
View profileBest model in the overall indexClaude Opus 5.5
Overall index 126.1, rank 1. $4 input and $20 output per 1M tokens.
Haiku 5.5 vs. Claude Opus 5.5Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
A: Claude Haiku 5.5B: DeepSeek-V4-Pro
AA-BriefcaseOverall · higher is betterClaude Haiku 5.5: 1,574.12 eloDeepSeek-V4-Pro: 1,253.16 eloArtificial AnalysisAs of 11/06/2026
AA-OmniscienceOverall · higher is betterClaude Haiku 5.5: 12.3 pointsDeepSeek-V4-Pro: -6.367 pointsArtificial AnalysisAs of 11/06/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Haiku 5.5: 34.7%DeepSeek-V4-Pro: 45.2%Artificial AnalysisAs of 11/06/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Haiku 5.5: 34.2%DeepSeek-V4-Pro: 94.1%Artificial AnalysisAs of 11/06/2026
AutomationBench-AAOverall · higher is betterClaude Haiku 5.5: 35.4%DeepSeek-V4-Pro: 56.7%Artificial AnalysisAs of 11/06/2026
Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.6%DeepSeek-V4-Pro: 26.2%Vals AIAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Haiku 5.5: 43.5%DeepSeek-V4-Pro: 23.5%Artificial AnalysisAs of 11/06/2026
EMBOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59%DeepSeek-V4-Pro: 51.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%DeepSeek-V4-Pro: 44.1%Vals AIAs of 10/29/2026
FrontierCodeOverall · higher is betterClaude Haiku 5.5: 34.9%DeepSeek-V4-Pro: 17.1%Artificial AnalysisAs of 11/06/2026
Show 54 more benchmarks
FrontierCode 1.1 MainOverall · higher is betterClaude Haiku 5.5: 41.8%DeepSeek-V4-Pro: 38.8%Artificial AnalysisAs of 11/06/2026
GDP.pdfOverall · higher is betterClaude Haiku 5.5: 20.8%DeepSeek-V4-Pro: 11.4%Artificial AnalysisAs of 11/06/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,630.83 eloDeepSeek-V4-Pro: 1,457.37 eloArtificial AnalysisAs of 11/06/2026
HLE-DiamondOverall · higher is betterClaude Haiku 5.5: 29.6%DeepSeek-V4-Pro: 19.5%Artificial AnalysisAs of 11/06/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 43.8%DeepSeek-V4-Pro: 23.1%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,589DeepSeek-V4-Pro: 1,447LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,425DeepSeek-V4-Pro: 1,458LMArenaAs of 10/28/2026
MedCodeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.5%DeepSeek-V4-Pro: 40.5%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.5%DeepSeek-V4-Pro: 75.1%Vals AIAs of 10/29/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89%DeepSeek-V4-Pro: 16%Vals AIAs of 10/29/2026
Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.2%DeepSeek-V4-Pro: 62.9%Vals AIAs of 10/12/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 31.9%DeepSeek-V4-Pro: 25.2%Vals AIAs of 11/05/2026
Terminal-BenchOverall · higher is betterClaude Haiku 5.5: 32.8%DeepSeek-V4-Pro: 14.1%Artificial AnalysisAs of 11/06/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.4%DeepSeek-V4-Pro: 11.1%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceOverall · higher is betterClaude Haiku 5.5: 20.0%DeepSeek-V4-Pro: 5.7%Artificial AnalysisAs of 11/06/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%DeepSeek-V4-Pro: 49.9%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.1%DeepSeek-V4-Pro: 15.5%Vals AIAs of 10/29/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.9%DeepSeek-V4-Pro: 57.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 49.6%DeepSeek-V4-Pro: 41.6%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50%DeepSeek-V4-Pro: 28.8%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevOverall · higher is betterClaude Haiku 5.5: 1,589DeepSeek-V4-Pro: 1,464LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterClaude Haiku 5.5: 1,425DeepSeek-V4-Pro: 1,455LMArenaAs of 10/28/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.5%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 6.7%DeepSeek-V4-Pro: 12.3%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70%DeepSeek-V4-Pro: 58.4%Vals AIAs of 10/29/2026
EMBDataroom · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 85.5%DeepSeek-V4-Pro: 62.6%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 42.9%DeepSeek-V4-Pro: 31.4%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 88.7%DeepSeek-V4-Pro: 83.4%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,568DeepSeek-V4-Pro: 1,435LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,435DeepSeek-V4-Pro: 1,459LMArenaAs of 10/28/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%DeepSeek-V4-Pro: 54.8%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 25%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 4.825 / 5DeepSeek-V4-Pro: 3.401 / 5Vals AIAs of 10/29/2026
EMBDCF · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 55.1%DeepSeek-V4-Pro: 44.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 45.3%DeepSeek-V4-Pro: 39.6%Vals AIAs of 10/29/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.2%DeepSeek-V4-Pro: 23.3%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevHTML development · higher is betterClaude Haiku 5.5: 1,568DeepSeek-V4-Pro: 1,471LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Haiku 5.5: 1,435DeepSeek-V4-Pro: 1,448LMArenaAs of 10/28/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 78.7%DeepSeek-V4-Pro: 47.8%Vals AIAs of 11/05/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.7%DeepSeek-V4-Pro: 36.6%Vals AIAs of 11/05/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.6%DeepSeek-V4-Pro: 3%Vals AIAs of 11/05/2026
EMBLBO · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 28.2%DeepSeek-V4-Pro: 43.9%Vals AIAs of 10/20/2026
Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 64.3%DeepSeek-V4-Pro: 52.6%Vals AIAs of 10/29/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 87%DeepSeek-V4-Pro: 86.5%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,608DeepSeek-V4-Pro: 1,440LMArenaAs of 10/28/2026
LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 1,468DeepSeek-V4-Pro: 1,489LMArenaAs of 10/28/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 56.2%DeepSeek-V4-Pro: 65.7%Vals AIAs of 11/05/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 18.5%DeepSeek-V4-Pro: 7.4%Vals AIAs of 11/05/2026
EMBM&A · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 57.8%DeepSeek-V4-Pro: 48.2%Vals AIAs of 10/20/2026
Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 73.5%DeepSeek-V4-Pro: 59.8%Vals AIAs of 10/29/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 40.7%DeepSeek-V4-Pro: 33.3%Vals AIAs of 11/05/2026
More comparisons
Compare Claude Haiku 5.5 and DeepSeek-V4-Pro with the models people compare them with most often.
Compare another matchup
Predecessor and successor
The most popular comparisons
- 1Claude Haiku 5.5 vs. GPT-6 Luna
- 2Claude Opus 5.5 vs. DeepSeek-V4-Pro
- 3Claude Sonnet 5.5 vs. Claude Haiku 5.5
- 4Claude Haiku 5.5 vs. DeepSeek V4.1 Flash 1017
- 5Claude Haiku 5.5 vs. DeepSeek-V4-Flash
- 6Claude Haiku 5.5 vs. DeepSeek-V4.1-Flash
- 7Claude Opus 5.5 vs. Claude Haiku 5.5
- 8GPT-6 Luna vs. DeepSeek-V4-Pro
- 9Claude Haiku 5.5 vs. GLM-5.3
Show all 54 comparisons
- 10Claude Haiku 5.5 vs. Gemini 3.5 Flash-Lite
- 11Claude Haiku 5.5 vs. Gemini 3.8 Flash
- 12Claude Sonnet 5.5 vs. DeepSeek-V4-Pro
- 13Claude Haiku 5.5 vs. Claude Sonnet 4.5
- 14Gemini 3.8 Flash vs. DeepSeek-V4-Pro
- 15Claude Opus 5 vs. DeepSeek-V4-Pro
- 16Claude Haiku 5.5 vs. Claude Sonnet 5
- 17DeepSeek-V4-Pro vs. DeepSeek-V4.1-Flash
- 18Claude Haiku 5.5 vs. Claude Opus 5
- 19Claude Haiku 5.5 vs. GPT-6 Astra
- 20Claude Haiku 5.5 vs. Gemini 3.5 Flash
- 21Claude Haiku 5.5 vs. Claude Opus 4.8
- 22DeepSeek-V4-Pro vs. Qwen 3.8 Max 0902
- 23Claude Haiku 5.5 vs. Gemini 4 Argon
- 24Claude Haiku 5.5 vs. Grok 4.7
- 25DeepSeek-V4-Pro vs. Kimi K3
- 26Claude Haiku 5.5 vs. GPT-5.6 Luna
- 27Claude Haiku 5.5 vs. Qwen 3.8 Max 0902
- 28Grok 4.7 vs. DeepSeek-V4-Pro
- 29GPT-6.1 Sol vs. DeepSeek-V4-Pro
- 30Claude Haiku 5.5 vs. Muse Spark 1.3
- 31Claude Haiku 5.5 vs. Claude Sonnet 4.6
- 32Claude Haiku 5.5 vs. Gemini 3.7 Flash
- 33Claude Haiku 5.5 vs. Mistral Large 4
- 34GPT-5.6 Sol vs. DeepSeek-V4-Pro
- 35Gemini 4 Argon vs. DeepSeek-V4-Pro
- 36Claude Haiku 5.5 vs. GPT-6.1 Sol
- 37GPT-6 Sol vs. DeepSeek-V4-Pro
- 38DeepSeek-V4-Pro vs. GLM-5.3
- 39DeepSeek-V4-Pro vs. GLM-5.3-Flash
- 40Claude Haiku 5.5 vs. Gemini 3.1 Pro Preview
- 41Claude Haiku 5.5 vs. GLM-5.3-Flash
- 42DeepSeek-V4-Pro vs. DeepSeek-V4-Flash
- 43Claude Haiku 5.5 vs. GPT-5.6 Sol
- 44Claude Haiku 5.5 vs. Gemini 3.6 Flash
- 45Claude Haiku 5.5 vs. Claude Opus 4.6
- 46DeepSeek-V4-Pro vs. DeepSeek V4.1 Flash 1017
- 47Claude Haiku 5.5 vs. Kimi K2.6
- 48DeepSeek-V4-Pro vs. Mistral Large 4
- 49Gemini 3.7 Flash vs. DeepSeek-V4-Pro
- 50Claude Haiku 5.5 vs. Claude Opus 4.7
- 51Claude Haiku 5.5 vs. Mistral Large 3
- 52Claude Haiku 5.5 vs. GPT-5.5
- 53Claude Haiku 5.5 vs. GPT-6.1 Terra
- 54Muse Wonder Full vs. DeepSeek-V4-Pro