Claude 4.5 Haiku (Reasoning) vs DeepSeek V4 Pro 0813 (Non-reasoning)

Mana yang lebih baik untuk uang: Claude 4.5 Haiku (Reasoning) oleh Anthropic atau DeepSeek V4 Pro 0813 (Non-reasoning) oleh DeepSeek? Kecerdasan, total biaya benchmark, dan waktu end-to-end dari Artificial Analysis & sumber lain, cuplikan 2026-10-26.

Pemenang jelas
AnthropicClaude 4.5 Haiku (Reasoning)Di luar batas Pareto
Skor kecerdasan (Intelligence Index)
16.90
Biaya benchmark (USD)
$594
DeepSeekDeepSeek V4 Pro 0813 (Non-reasoning)Di luar batas Pareto
Skor kecerdasan (Intelligence Index)
20.40
Biaya benchmark (USD)
$451
Kesimpulan

Pilih DeepSeek V4 Pro 0813 (Non-reasoning)

DeepSeek V4 Pro 0813 (Non-reasoning) dibanding Claude 4.5 Haiku (Reasoning): kecerdasan 20.7% lebih tinggi, biaya menjalankan benchmark AA 24.1% lebih rendah, dan waktu total 73.0% lebih cepat.

MetrikClaude 4.5 Haiku (Reasoning)DeepSeek V4 Pro 0813 (Non-reasoning)Selisih
Kecerdasan (lebih tinggi lebih baik)16.920.4+20.7% DeepSeek V4 Pro 0813 … 20.7% lebih cerdas
Total biaya AA (lebih rendah lebih baik)$594.08$450.76−24.1% DeepSeek V4 Pro 0813 … 24.1% lebih murah
Waktu ujung ke ujung (lebih rendah lebih baik)24.36s6.58s−73.0% DeepSeek V4 Pro 0813 … 73.0% lebih cepat
Harga per 1 juta token (masuk/keluar)$1.00 / $5.00$1.32 / $3.96
Jenis inputTeks, GambarTeks
Buka pertarungan ini di pemilih interaktifClaude 4.5 Haiku (Reasoning): model apa yang mengunggulinyaDeepSeek V4 Pro 0813 (Non-reasoning): model apa yang mengunggulinya
Pareto frontier hari ini

Dibandingkan dengan batas Pareto

0204060$10$20$50$100$200$500$1k$2k$5k$10k$20kBiaya untuk menjalankan Artificial Analysis Intelligence Index (USD, skala log)Indeks kecerdasanApodex 1.1 (Apodex): kecerdasan 26.40, $939Beam 1.0 (Reflection): kecerdasan 30.30, $319Celeris-1 (Celeris): kecerdasan 6.30, $60.0Claude 4.5 Sonnet (Reasoning) (Anthropic): kecerdasan 20.70, $1501Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic): kecerdasan 49.60, $11161Claude Fable 5.1 (High, Default Fallback) (Anthropic): kecerdasan 51.20, $5242Claude Fable 5.1 (Low, Default Fallback) (Anthropic): kecerdasan 46.80, $3158Claude Fable 5.1 (Max, Default Fallback) (Anthropic): kecerdasan 53.40, $13129Claude Fable 5.1 (Medium, Default Fallback) (Anthropic): kecerdasan 48.90, $3983Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic): kecerdasan 53.20, $9063Claude Haiku 5.5 (Low) (Anthropic): kecerdasan 29.50, $34.3Claude Haiku 5.5 (Max) (Anthropic): kecerdasan 43.40, $330Claude Opus 4.8 (Max) (Anthropic): kecerdasan 41.80, $6874Claude Opus 5 (High) (Anthropic): kecerdasan 48.10, $4332Claude Opus 5 (Low) (Anthropic): kecerdasan 39.40, $1561Claude Opus 5 (Max) (Anthropic): kecerdasan 50.80, $7275Claude Opus 5 (Medium) (Anthropic): kecerdasan 44.80, $2732Claude Opus 5 (Xhigh) (Anthropic): kecerdasan 49.70, $5868Claude Opus 5.5 (Low, Default Fallback) (Anthropic): kecerdasan 42.30, $860Claude Opus 5.5 (Medium, Default Fallback) (Anthropic): kecerdasan 51.20, $1627Claude Sonnet 4.6 (Max) (Anthropic): kecerdasan 30.10, $4925Claude Sonnet 5 (High) (Anthropic): kecerdasan 31.70, $2086Claude Sonnet 5 (Low) (Anthropic): kecerdasan 24.30, $653Claude Sonnet 5 (Max) (Anthropic): kecerdasan 38.20, $6998Claude Sonnet 5 (Medium) (Anthropic): kecerdasan 28.10, $1218Claude Sonnet 5 (Xhigh) (Anthropic): kecerdasan 34.40, $3255Claude Sonnet 5.5 (High, Default Fallback) (Anthropic): kecerdasan 46.80, $1027Claude Sonnet 5.5 (Low, Default Fallback) (Anthropic): kecerdasan 35.90, $482Claude Sonnet 5.5 (Max, Default Fallback) (Anthropic): kecerdasan 56.00, $7260Claude Sonnet 5.5 (Medium, Default Fallback) (Anthropic): kecerdasan 40.80, $622Claude Sonnet 5.5 (Xhigh, Default Fallback) (Anthropic): kecerdasan 51.90, $2177DeepSeek R1 (Jan '25) (DeepSeek): kecerdasan 11.40, $461DeepSeek V3 (Dec '24) (DeepSeek): kecerdasan 8.50, $25.4DeepSeek V3 0324 (DeepSeek): kecerdasan 9.70, $19.9DeepSeek V4 Flash 0420 (High) (DeepSeek): kecerdasan 24.40, $121DeepSeek V4 Flash 0420 (Max) (DeepSeek): kecerdasan 24.20, $149DeepSeek V4 Flash 0731 (Max) (DeepSeek): kecerdasan 34.30, $200DeepSeek V4 Flash Vision (Max) (DeepSeek): kecerdasan 34.80, $1081DeepSeek V4 Pro 0424 (Max) (DeepSeek): kecerdasan 30.40, $277DeepSeek V4 Pro 0813 (Max) (DeepSeek): kecerdasan 36.00, $1122DeepSeek V4.1 Flash (Max) (DeepSeek): kecerdasan 39.50, $672DeepSeek V4.1 Flash (Non-reasoning) (DeepSeek): kecerdasan 24.70, $239DeepSeek V4.1 Flash 1017 (Max) (DeepSeek): kecerdasan 45.10, $445Gemini 2.5 Pro (Google): kecerdasan 16.10, $823Gemini 3.1 Flash-Lite (Google): kecerdasan 15.60, $156Gemini 3.1 Pro Preview (Google): kecerdasan 29.70, $1935Gemini 3.5 Flash (High) (Google): kecerdasan 32.60, $4222Gemini 3.5 Flash-Lite (Google): kecerdasan 22.20, $366Gemini 3.6 Flash (High) (Google): kecerdasan 34.00, $1614Gemini 3.8 Flash (High) (Google): kecerdasan 40.90, $1623Gemini 3.8 Flash (Medium) (Google): kecerdasan 39.80, $1100Gemini 4 Argon (High) (Google): kecerdasan 52.60, $2407Gemma 4 E4B (Reasoning) (Google): kecerdasan 8.90, $14.7GLM-5.1 (Reasoning) (Z AI): kecerdasan 26.10, $1487GLM-5.2 (Max) (Z AI): kecerdasan 33.70, $2097GLM-5.3 (Low) (Z AI): kecerdasan 34.30, $1013GLM-5.3 (Max) (Z AI): kecerdasan 44.80, $2503GLM-5.3-Flash (Z AI): kecerdasan 41.80, $306GPT-5 mini (High) (OpenAI): kecerdasan 16.80, $189GPT-5.4 mini (Xhigh) (OpenAI): kecerdasan 24.10, $1524GPT-5.4 nano (Xhigh) (OpenAI): kecerdasan 20.70, $331GPT-5.5 (High) (OpenAI): kecerdasan 37.00, $3411GPT-5.5 (Medium) (OpenAI): kecerdasan 33.80, $2095GPT-5.5 (Xhigh) (OpenAI): kecerdasan 38.40, $5294GPT-5.5 Instant (June 2026) (OpenAI): kecerdasan 26.00, $1184GPT-5.6 Luna (High) (OpenAI): kecerdasan 32.10, $108GPT-5.6 Luna (Low) (OpenAI): kecerdasan 21.00, $27.0GPT-5.6 Luna (Max) (OpenAI): kecerdasan 37.30, $320GPT-5.6 Luna (Medium) (OpenAI): kecerdasan 25.00, $44.3GPT-5.6 Luna (Non-reasoning) (OpenAI): kecerdasan 15.50, $23.0GPT-5.6 Luna (Xhigh) (OpenAI): kecerdasan 34.60, $179GPT-5.6 Sol (High) (OpenAI): kecerdasan 42.30, $1487GPT-5.6 Sol (Low) (OpenAI): kecerdasan 33.50, $637GPT-5.6 Sol (Max) (OpenAI): kecerdasan 47.00, $3465GPT-5.6 Sol (Medium) (OpenAI): kecerdasan 39.20, $997GPT-5.6 Sol (Xhigh) (OpenAI): kecerdasan 44.00, $2082GPT-5.6 Terra (High) (OpenAI): kecerdasan 34.20, $768GPT-5.6 Terra (Low) (OpenAI): kecerdasan 27.50, $350GPT-5.6 Terra (Max) (OpenAI): kecerdasan 42.10, $2501GPT-5.6 Terra (Medium) (OpenAI): kecerdasan 30.10, $447GPT-5.6 Terra (Non-reasoning) (OpenAI): kecerdasan 20.80, $256GPT-5.6 Terra (Xhigh) (OpenAI): kecerdasan 38.00, $1187GPT-6 Astra (High) (OpenAI): kecerdasan 50.90, $2925GPT-6 Astra (Low) (OpenAI): kecerdasan 45.80, $1537GPT-6 Astra (Max) (OpenAI): kecerdasan 52.70, $5324GPT-6 Astra (Medium) (OpenAI): kecerdasan 49.60, $2434GPT-6 Astra (Xhigh) (OpenAI): kecerdasan 52.40, $3803GPT-6 Luna (Non-reasoning) (OpenAI): kecerdasan 18.50, $19.2GPT-6 Sol (High) (OpenAI): kecerdasan 42.40, $605GPT-6 Sol (Low) (OpenAI): kecerdasan 34.20, $269GPT-6 Sol (Max) (OpenAI): kecerdasan 47.60, $1536GPT-6 Sol (Medium) (OpenAI): kecerdasan 39.80, $416GPT-6 Sol (Non-reasoning) (OpenAI): kecerdasan 28.50, $449GPT-6 Sol (Xhigh) (OpenAI): kecerdasan 44.20, $855GPT-6.1 Sol (Low) (OpenAI): kecerdasan 42.10, $250gpt-oss-120b (High) (OpenAI): kecerdasan 11.60, $123gpt-oss-20b (High) (OpenAI): kecerdasan 9.00, $28.8Granite 4.2 30B (IBM): kecerdasan 12.70, $111Granite 4.2 3B (IBM): kecerdasan 9.10, $14.9Granite 4.2 8B (IBM): kecerdasan 11.10, $53.1Grok 4.3 (High) (SpaceXAI): kecerdasan 24.90, $363Grok 4.3 (Non-reasoning) (SpaceXAI): kecerdasan 14.00, $250Grok 4.5 (High) (SpaceXAI): kecerdasan 38.80, $1244Grok 4.6 (High) (SpaceXAI): kecerdasan 44.30, $1963Grok 4.6 (Low) (SpaceXAI): kecerdasan 35.10, $614Grok 4.6 (Medium) (SpaceXAI): kecerdasan 42.80, $1557Grok 4.6 (Xhigh) (SpaceXAI): kecerdasan 44.20, $2242Grok 4.7 (High) (SpaceXAI): kecerdasan 46.30, $3881Grok 4.7 (Low) (SpaceXAI): kecerdasan 42.20, $1631Grok 4.7 (Xhigh) (SpaceXAI): kecerdasan 46.40, $4967Hy3 (Tencent): kecerdasan 25.30, $150Inkling Small (Thinking Machines): kecerdasan 25.70, $241Kimi K2.6 (Reasoning) (Kimi): kecerdasan 27.00, $1528Kimi K2.7 Code (Kimi): kecerdasan 25.80, $993Kimi K3 (Low) (Kimi): kecerdasan 30.10, $1190Kimi K3 (Max) (Kimi): kecerdasan 43.60, $3658Ling 3.1 Flash (InclusionAI): kecerdasan 41.10, $1015Ling 3.1 Flash 1019 (InclusionAI): kecerdasan 43.90, $1552Llama 4 Maverick (Meta): kecerdasan 9.30, $44.0Llama 4 Scout (Meta): kecerdasan 6.50, $73.6LongCat 2.0 (LongCat): kecerdasan 19.10, $545Mercury 2 (Inception): kecerdasan 10.80, $105Mercury 2.5 (Inception): kecerdasan 12.30, $218MiMo-V2.5 (Xiaomi): kecerdasan 21.80, $61.9MiMo-V2.5-Pro (Reasoning) (Xiaomi): kecerdasan 26.00, $231MiniMax-M3 (MiniMax): kecerdasan 29.20, $538MiniMax-M3.1-Flash (MiniMax): kecerdasan 42.70, $283Ministral 3 14B (Mistral): kecerdasan 6.00, $37.6Ministral 3 3B (Mistral): kecerdasan 4.80, $12.2Ministral 3 8B (Mistral): kecerdasan 5.50, $27.5Mistral Large 3 (Mistral): kecerdasan 9.30, $46.4Mistral Large 4 Preview (Mistral): kecerdasan 38.40, $1608Mistral Medium 3.5 (Mistral): kecerdasan 14.20, $1264Mistral Small 3.1 (Mistral): kecerdasan 7.10, $27.8Mistral Small 3.2 (Mistral): kecerdasan 7.00, $122Mistral Small 4 (Reasoning) (Mistral): kecerdasan 11.30, $42.5Muse Glimmer (High) (Meta): kecerdasan 17.50, $146Muse Spark 1.1 (Xhigh) (Meta): kecerdasan 33.70, $1737Muse Spark 1.2 (Xhigh) (Meta): kecerdasan 39.60, $1385Muse Spark 1.3 (Max) (Meta): kecerdasan 48.10, $2000Muse Spark 1.3 (Xhigh) (Meta): kecerdasan 45.10, $1655Muse Spark Open (Xhigh) (Meta): kecerdasan 38.90, $1185Muse Wonder (Max) (Meta): kecerdasan 52.40, $5787Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA): kecerdasan 12.80, $1319Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA): kecerdasan 22.90, $697Nemotron 3.5 Lightning (NVIDIA): kecerdasan 12.90, $92.8Nemotron 3.5 Super VL (NVIDIA): kecerdasan 26.50, $286NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA): kecerdasan 8.90, $63.7Qwen3 Coder Next (Alibaba): kecerdasan 9.20, $405Qwen3.5 122B A10B (Reasoning) (Alibaba): kecerdasan 15.60, $661Qwen3.5 397B A17B (Reasoning) (Alibaba): kecerdasan 18.40, $941Qwen3.5 9B (Reasoning) (Alibaba): kecerdasan 11.20, $329Qwen3.6 27B (Reasoning) (Alibaba): kecerdasan 21.40, $1145Qwen3.6 35B A3B (Reasoning) (Alibaba): kecerdasan 18.20, $896Qwen3.7 Max (Alibaba): kecerdasan 29.50, $2277Qwen3.7 Plus (Alibaba): kecerdasan 25.20, $428Qwen3.8 2.4T A95B (Alibaba): kecerdasan 39.90, $2632Qwen3.8 27B (Low) (Alibaba): kecerdasan 26.20, $1060Qwen3.8 27B (Medium) (Alibaba): kecerdasan 27.60, $1165Qwen3.8 27B (Non-reasoning) (Alibaba): kecerdasan 20.20, $2022Qwen3.8 27B (Xhigh) (Alibaba): kecerdasan 33.70, $1336Qwen3.8 Max (Alibaba): kecerdasan 40.20, $3172Qwen3.8 Max (0902) (Alibaba): kecerdasan 45.40, $4935Qwen3.8-Flash-Next (Alibaba): kecerdasan 39.80, $363Ring-2.6-1T (InclusionAI): kecerdasan 16.60, $576Solar Mini 4 (Upstage): kecerdasan 24.10, $502Solar Pro 3 (Upstage): kecerdasan 7.80, $159Solar Pro 4 (Upstage): kecerdasan 26.60, $737Step 5 Preview (StepFun): kecerdasan 43.70, $1190Trinity Large Thinking (Arcee AI): kecerdasan 10.80, $233GPT-6 Luna (Low) (OpenAI): kecerdasan 21.50, $10.6GPT-6 Luna (Medium) (OpenAI): kecerdasan 29.90, $31.2GPT-6 Luna (High) (OpenAI): kecerdasan 32.90, $47.9Claude Haiku 5.5 (Medium) (Anthropic): kecerdasan 34.50, $56.4GPT-6 Luna (Xhigh) (OpenAI): kecerdasan 34.60, $66.8Claude Haiku 5.5 (High) (Anthropic): kecerdasan 37.80, $94.1MiMo-V2.6-Flash (Xiaomi): kecerdasan 37.90, $110GPT-6 Luna (Max) (OpenAI): kecerdasan 38.10, $122Claude Haiku 5.5 (Xhigh) (Anthropic): kecerdasan 41.20, $158MiMo-V2.6-Pro (Xiaomi): kecerdasan 46.30, $207GPT-6.1 Sol (Medium) (OpenAI): kecerdasan 47.80, $361GPT-6.1 Sol (High) (OpenAI): kecerdasan 50.20, $521GPT-6.1 Sol (Xhigh) (OpenAI): kecerdasan 51.00, $662GPT-6.1 Sol (Max) (OpenAI): kecerdasan 51.80, $1082Claude Opus 5.5 (High, Default Fallback) (Anthropic): kecerdasan 53.60, $2172Kimi K3.1 Pro (Kimi): kecerdasan 55.10, $3117Claude Opus 5.5 (Xhigh, Default Fallback) (Anthropic): kecerdasan 56.00, $4057Claude Opus 5.5 (Max, Default Fallback) (Anthropic): kecerdasan 57.60, $8708DeepSeek V4 Pro 0813 (Non-reasoning) (DeepSeek): kecerdasan 20.40, $451Claude 4.5 Haiku (Reasoning) (Anthropic): kecerdasan 16.90, $594Claude 4.5 Haiku (Reasoning)DeepSeek V4 Pro 0813 (Non-reasoning)GPT-6 Luna (Low)Claude Opus 5.5 (Max, Default Fallback)
Claude 4.5 Haiku (Reasoning)DeepSeek V4 Pro 0813 (Non-reasoning)Pareto frontier hari iniBatas Pareto model dengan bobot yang dapat diunduh (open-weights frontier)Semua model lainnya
Perbandingan langsung

Bandingkan sesuatu yang lain

Agen: Accept: text/markdown or ?format=md mengembalikan halaman ini sebagai Markdown. JSON: /api/v1/compare/claude-4-5-haiku-reasoning/deepseek-v4-pro-non-reasoning · Markdown: /api/v1/compare/claude-4-5-haiku-reasoning/deepseek-v4-pro-non-reasoning?format=md · llms.txt · keterampilan agen