Inkling Small vs Trinity Large Thinking

Mana yang lebih baik untuk uang: Inkling Small oleh Thinking Machines atau Trinity Large Thinking oleh Arcee AI? Kecerdasan, total biaya benchmark, dan waktu end-to-end dari Artificial Analysis & sumber lain, cuplikan 2026-09-09.

Pemenang jelas
Thinking MachinesInkling SmallDi luar batas Pareto
Skor kecerdasan (Intelligence Index)
26.10
Biaya benchmark (USD)
$241
Arcee AITrinity Large ThinkingDi luar batas Pareto
Skor kecerdasan (Intelligence Index)
10.90
Biaya benchmark (USD)
$518
Kesimpulan

Pilih Inkling Small

Trinity Large Thinking dibanding Inkling Small: kecerdasan 58.2% lebih rendah, biaya menjalankan benchmark AA 115.1% lebih tinggi, dan waktu total 59.9% lebih cepat.

MetrikInkling SmallTrinity Large ThinkingSelisih
Kecerdasan (lebih tinggi lebih baik)26.110.9−58.2% Trinity Large Thinking 58.2% kurang cerdas
Total biaya AA (lebih rendah lebih baik)$240.85$518.07+115.1% Trinity Large Thinking 2.2 kali lebih mahal
Waktu ujung ke ujung (lebih rendah lebih baik)21.89s8.78s−59.9% Trinity Large Thinking 59.9% lebih cepat
Harga per 1 juta token (masuk/keluar)$0.30 / $1.20$0.25 / $0.90
Jenis inputTidak dilaporkanTidak dilaporkan
Buka pertarungan ini di pemilih interaktifInkling Small: model apa yang mengunggulinyaTrinity Large Thinking: model apa yang mengunggulinya
Pareto frontier hari ini

Dibandingkan dengan batas Pareto

0102030405060$20$50$100$200$500$1k$2k$5k$10k$20kBiaya untuk menjalankan Artificial Analysis Intelligence Index (USD, skala log)Indeks kecerdasanCeleris-1 (Celeris): kecerdasan 6.30, $60.0Claude 4.5 Haiku (Reasoning) (Anthropic): kecerdasan 17.60, $524Claude 4.5 Sonnet (Reasoning) (Anthropic): kecerdasan 21.20, $1501Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (Anthropic): kecerdasan 49.70, $11161Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) (Anthropic): kecerdasan 51.20, $5242Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback) (Anthropic): kecerdasan 47.00, $3158Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) (Anthropic): kecerdasan 49.10, $3983Claude Opus 4.8 (Adaptive Reasoning, Max Effort) (Anthropic): kecerdasan 42.00, $6874Claude Opus 5 (Adaptive Reasoning, High Effort) (Anthropic): kecerdasan 48.20, $4332Claude Opus 5 (Adaptive Reasoning, Low Effort) (Anthropic): kecerdasan 39.80, $1561Claude Opus 5 (Adaptive Reasoning, Max Effort) (Anthropic): kecerdasan 50.70, $7275Claude Opus 5 (Adaptive Reasoning, Medium Effort) (Anthropic): kecerdasan 45.10, $2732Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) (Anthropic): kecerdasan 49.70, $5868Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) (Anthropic): kecerdasan 30.50, $4925Claude Sonnet 5 (Adaptive Reasoning, Low Effort) (Anthropic): kecerdasan 24.70, $653Claude Sonnet 5 (Adaptive Reasoning, Max Effort) (Anthropic): kecerdasan 38.40, $6998Claude Sonnet 5 (Adaptive Reasoning, Medium Effort) (Anthropic): kecerdasan 28.40, $1218DeepSeek R1 (Jan '25) (DeepSeek): kecerdasan 11.40, $461DeepSeek V3 (Dec '24) (DeepSeek): kecerdasan 8.50, $25.4DeepSeek V3 0324 (DeepSeek): kecerdasan 9.70, $87.2DeepSeek V4 Flash (Reasoning, High Effort) (DeepSeek): kecerdasan 24.80, $210DeepSeek V4 Flash (Reasoning, Max Effort) (DeepSeek): kecerdasan 24.60, $191DeepSeek V4 Flash 0731 (Reasoning, Max Effort) (DeepSeek): kecerdasan 34.50, $474DeepSeek V4 Flash Vision (Reasoning, Max Effort) (DeepSeek): kecerdasan 35.00, $445DeepSeek V4 Pro (Reasoning, Max Effort) (DeepSeek): kecerdasan 30.90, $277DeepSeek V4 Pro 0813 (Reasoning, Max Effort) (DeepSeek): kecerdasan 36.30, $1122Gemini 2.5 Pro (Google): kecerdasan 16.70, $707Gemini 3.1 Flash-Lite (Google): kecerdasan 16.00, $119Gemini 3.1 Pro Preview (Google): kecerdasan 30.40, $1310Gemini 3.5 Flash (high) (Google): kecerdasan 33.00, $2172Gemini 3.5 Flash-Lite (Google): kecerdasan 22.70, $267Gemini 3.6 Flash (high) (Google): kecerdasan 34.30, $1037Gemini 3.7 Flash (high) (Google): kecerdasan 39.40, $1084Gemini 3.8 Flash (high) (Google): kecerdasan 41.20, $1623Gemini 3.8 Flash (medium) (Google): kecerdasan 40.00, $1100GLM-5.3 (max) (Z AI): kecerdasan 44.90, $2503GPT-5 mini (high) (OpenAI): kecerdasan 17.40, $189GPT-5.4 mini (xhigh) (OpenAI): kecerdasan 24.60, $1438GPT-5.4 nano (xhigh) (OpenAI): kecerdasan 21.20, $331GPT-5.5 (high) (OpenAI): kecerdasan 37.30, $3411GPT-5.5 (medium) (OpenAI): kecerdasan 34.20, $2095GPT-5.5 (xhigh) (OpenAI): kecerdasan 38.60, $5294GPT-5.5 Instant (June 2026) (OpenAI): kecerdasan 26.80, $1184GPT-5.6 Luna (max) (OpenAI): kecerdasan 37.50, $320GPT-5.6 Sol (low) (OpenAI): kecerdasan 33.80, $637GPT-5.6 Sol (max) (OpenAI): kecerdasan 47.10, $3465GPT-5.6 Sol (medium) (OpenAI): kecerdasan 39.50, $997GPT-5.6 Sol (xhigh) (OpenAI): kecerdasan 44.10, $2082GPT-5.6 Terra (high) (OpenAI): kecerdasan 34.50, $768GPT-5.6 Terra (max) (OpenAI): kecerdasan 42.30, $2501GPT-5.6 Terra (xhigh) (OpenAI): kecerdasan 38.20, $1187GPT-6 Astra (Non-reasoning) (OpenAI): kecerdasan 45.20, $2441gpt-oss-120b (high) (OpenAI): kecerdasan 12.30, $122gpt-oss-20b (high) (OpenAI): kecerdasan 9.00, $29.4Grok 4.3 (high) (SpaceXAI): kecerdasan 25.40, $332Grok 4.3 (Non-reasoning) (SpaceXAI): kecerdasan 14.50, $203Grok 4.5 (high) (SpaceXAI): kecerdasan 39.10, $1404Grok 4.6 (high) (SpaceXAI): kecerdasan 44.40, $2352Grok 4.6 (low) (SpaceXAI): kecerdasan 35.40, $761Grok 4.6 (medium) (SpaceXAI): kecerdasan 43.00, $1937Grok 4.6 (xhigh) (SpaceXAI): kecerdasan 44.30, $2830Hy3 (Tencent): kecerdasan 25.80, $149Inkling (xhigh) (Thinking Machines): kecerdasan 25.50, $1026Kimi K2.7 Code (Kimi): kecerdasan 26.30, $993Kimi K3 (max) (Kimi): kecerdasan 43.80, $3658Llama 4 Maverick (Meta): kecerdasan 9.30, $45.5Llama 4 Scout (Meta): kecerdasan 6.50, $77.6LongCat 2.0 (LongCat): kecerdasan 19.70, $545Mercury 2 (Inception): kecerdasan 11.50, $153MiniMax-M2.7 (MiniMax): kecerdasan 23.20, $236MiniMax-M3 (MiniMax): kecerdasan 29.60, $538Ministral 3 14B (Mistral): kecerdasan 6.00, $250Ministral 3 3B (Mistral): kecerdasan 4.80, $61.3Ministral 3 8B (Mistral): kecerdasan 5.50, $169Mistral Large 3 (Mistral): kecerdasan 9.70, $130Mistral Medium 3.5 (Mistral): kecerdasan 14.90, $1160Mistral Small 3.1 (Mistral): kecerdasan 7.40, $35.8Mistral Small 3.2 (Mistral): kecerdasan 7.00, $163Mistral Small 4 (Reasoning) (Mistral): kecerdasan 11.50, $78.7Muse Glimmer (high) (Meta): kecerdasan 18.10, $152Muse Spark 1.1 (xhigh) (Meta): kecerdasan 34.30, $1737Muse Spark 1.2 (xhigh) (Meta): kecerdasan 39.80, $1385Muse Spark 1.3 (xhigh) (Meta): kecerdasan 45.20, $1655Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA): kecerdasan 13.60, $859Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA): kecerdasan 23.40, $801Nemotron 3.5 Lightning (NVIDIA): kecerdasan 13.60, $105NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA): kecerdasan 8.90, $63.7Quasar 438B (max, based on GLM-5.2) (Multiverse Computing): kecerdasan 27.10, $2504Qwen3 235B A22B 2507 (Reasoning) (Alibaba): kecerdasan 12.70, $235Qwen3 30B A3B 2507 (Reasoning) (Alibaba): kecerdasan 9.80, $188Qwen3 Coder Next (Alibaba): kecerdasan 10.10, $476Qwen3.5 122B A10B (Reasoning) (Alibaba): kecerdasan 16.20, $661Qwen3.5 397B A17B (Reasoning) (Alibaba): kecerdasan 19.10, $941Qwen3.6 27B (Reasoning) (Alibaba): kecerdasan 21.90, $1145Qwen3.7 Max (Alibaba): kecerdasan 29.90, $2277Qwen3.7 Plus (Alibaba): kecerdasan 25.80, $568Qwen3.8 2.4T A95B (Alibaba): kecerdasan 40.00, $2632Qwen3.8 27B (xhigh) (Alibaba): kecerdasan 33.90, $1170Qwen3.8 Max (Alibaba): kecerdasan 40.30, $3172Ring-2.6-1T (InclusionAI): kecerdasan 17.30, $576Solar Pro 3 (Upstage): kecerdasan 7.80, $159Granite 4.2 3B (IBM): kecerdasan 9.10, $14.9MiMo-V2.5 (Xiaomi): kecerdasan 22.30, $42.6MiMo-V2.5-Pro (Xiaomi): kecerdasan 26.40, $138GPT-5.6 Luna (xhigh) (OpenAI): kecerdasan 34.80, $179GLM-5.3-Flash (Z AI): kecerdasan 41.90, $280GPT-5.6 Sol (high) (OpenAI): kecerdasan 42.50, $1487GPT-6 Astra (low) (OpenAI): kecerdasan 46.00, $1537Muse Spark 1.3 (max) (Meta): kecerdasan 48.20, $2000GPT-6 Astra (medium) (OpenAI): kecerdasan 49.70, $2434GPT-6 Astra (high) (OpenAI): kecerdasan 51.00, $2917GPT-6 Astra (xhigh) (OpenAI): kecerdasan 52.50, $3803GPT-6 Astra (max) (OpenAI): kecerdasan 52.80, $5324Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (Anthropic): kecerdasan 53.20, $9063Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (Anthropic): kecerdasan 53.40, $13129Trinity Large Thinking (Arcee AI): kecerdasan 10.90, $518Inkling Small (Thinking Machines): kecerdasan 26.10, $241Inkling SmallTrinity Large ThinkingGranite 4.2 3BClaude Fable 5.1 (max)
Inkling SmallTrinity Large ThinkingPareto 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/inkling-small/trinity-large-thinking · Markdown: /api/v1/compare/inkling-small/trinity-large-thinking?format=md · llms.txt · keterampilan agen