https://pombench.com/2026-10-25T07:41:47.868693+00:00https://pombench.com/compare/2026-10-25T07:41:47.868693+00:00https://pombench.com/method/2026-10-25T07:41:47.868693+00:00https://pombench.com/animations/kimi-k3-1-pro/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/kimi-k3.1-pro/poster.pngKimi K3.1 Pro coding benchmark: PomBench Pomeranian animationKimi K3.1 Pro coding test: watch the animation it coded. 20,154 output tokens, known API cost $0.2058. Compare Kimi K3.1 Pro vs Kimi K3.https://pombench.com/results/kimi-k3.1-pro/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gemini-4-argon/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gemini-4-argon/poster.pngGemini 4 Argon coding benchmark: PomBench Pomeranian animationGemini 4 Argon coding test: watch the animation it coded. 51,473 output tokens, known API cost $0.5770. Compare Gemini 4 Argon vs Gemini 3.8 Flash.https://pombench.com/results/gemini-4-argon/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/muse-wonder/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/muse-wonder/poster.pngMuse Wonder coding benchmark: PomBench Pomeranian animationMuse Wonder coding test: watch the animation it coded. 8,480 output tokens, known API cost $0.1778. Compare Muse Wonder vs Llama 4 Maverick.https://pombench.com/results/muse-wonder/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-haiku-5-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-haiku-5-5/poster.pngClaude Haiku 5.5 coding benchmark: PomBench Pomeranian animationClaude Haiku 5.5 coding test: watch the animation it coded. 8,664 output tokens, known API cost $0.0047. Compare Claude Haiku 5.5 vs Claude Sonnet 5.5.https://pombench.com/results/claude-haiku-5-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/mistral-large-4/2026-10-25T07:41:47.868693+00:00https://pombench.com/results/mistral-large-4/poster.pngMistral Large 4 coding benchmark: PomBench Pomeranian animationMistral Large 4 coding test: watch the animation it coded. 175,024 output tokens, known API cost $0.7578. Compare Mistral Large 4 vs Mistral Medium 3.5.https://pombench.com/results/mistral-large-4/animation.mp4122026-10-25T07:41:47.868693+00:00yeshttps://pombench.com/animations/gpt-6-1-sol/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-6-1-sol/poster.pngGPT-6.1 Sol coding benchmark: PomBench Pomeranian animationGPT-6.1 Sol coding test: watch the animation it coded. 8,989 output tokens, known API cost $0.0950. Compare GPT-6.1 Sol vs GPT-6 Sol.https://pombench.com/results/gpt-6-1-sol/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-sonnet-5-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-sonnet-5-5/poster.pngClaude Sonnet 5.5 coding benchmark: PomBench Pomeranian animationClaude Sonnet 5.5 coding test: watch the animation it coded. 4,134 output tokens, known API cost $0.0480. Compare Claude Sonnet 5.5 vs Claude Opus 5.5.https://pombench.com/results/claude-sonnet-5-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-opus-5-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-opus-5-5/poster.pngClaude Opus 5.5 coding benchmark: PomBench Pomeranian animationClaude Opus 5.5 coding test: watch the animation it coded. 8,093 output tokens, known API cost $0.1751. Compare Claude Opus 5.5 vs Claude Sonnet 5.5.https://pombench.com/results/claude-opus-5-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-6-luna/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-6-luna/poster.pngGPT-6 Luna coding benchmark: PomBench Pomeranian animationGPT-6 Luna coding test: watch the animation it coded. 3,769 output tokens, known API cost $0.0021. Compare GPT-6 Luna vs GPT-6 Sol.https://pombench.com/results/gpt-6-luna/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-6-sol/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-6-sol/poster.pngGPT-6 Sol coding benchmark: PomBench Pomeranian animationGPT-6 Sol coding test: watch the animation it coded. 6,748 output tokens, known API cost $0.0726. Compare GPT-6 Sol vs GPT-6 Luna.https://pombench.com/results/gpt-6-sol/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/grok-4-7/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/grok-4-7/poster.pngGrok 4.7 coding benchmark: PomBench Pomeranian animationGrok 4.7 coding test: watch the animation it coded. 10,467 output tokens, known API cost $0.0669. Compare Grok 4.7 vs GPT-6.1 Sol.https://pombench.com/results/grok-4-7/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/xiaomi-mimo-v2-6-pro/2026-10-25T07:41:47.868693+00:00https://pombench.com/results/xiaomi-mimo-v2.6-pro/poster.pngXiaomi MiMo-V2.6-Pro coding benchmark: PomBench Pomeranian animationXiaomi MiMo-V2.6-Pro coding test: watch the animation it coded. 119,084 output tokens, known API cost $0.1207. Compare Xiaomi MiMo-V2.6-Pro vs Grok 4.7.https://pombench.com/results/xiaomi-mimo-v2.6-pro/animation.mp4122026-10-25T07:41:47.868693+00:00yeshttps://pombench.com/animations/deepseek-v4-1-flash/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/deepseek-v4-1-flash/poster.pngDeepSeek V4.1 Flash coding benchmark: PomBench Pomeranian animationDeepSeek V4.1 Flash coding test: watch the animation it coded. 8,357 output tokens, known API cost $0.0106. Compare DeepSeek V4.1 Flash vs DeepSeek V4 Pro.https://pombench.com/results/deepseek-v4-1-flash/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-6-astra/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-6-astra/poster.pngGPT-6 Astra coding benchmark: PomBench Pomeranian animationGPT-6 Astra coding test: watch the animation it coded. 10,275 output tokens, known API cost $0.5391. Compare GPT-6 Astra vs GPT-6 Luna.https://pombench.com/results/gpt-6-astra/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/qwen3-8-max/2026-10-25T07:41:47.868693+00:00https://pombench.com/results/qwen3.8-max/poster.pngQwen3.8 Max (0902) coding benchmark: PomBench Pomeranian animationQwen3.8 Max (0902) coding test: watch the animation it coded. 37,657 output tokens, known API cost $0.2314. Compare Qwen3.8 Max (0902) vs GPT-6 Astra.https://pombench.com/results/qwen3.8-max/animation.mp4122026-10-25T07:41:47.868693+00:00yeshttps://pombench.com/animations/gemini-3-8-flash/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gemini-3.8-flash/poster.pngGemini 3.8 Flash coding benchmark: PomBench Pomeranian animationGemini 3.8 Flash coding test: watch the animation it coded. 11,345 output tokens, known API cost $0.0441. Compare Gemini 3.8 Flash vs Gemini 4 Argon.https://pombench.com/results/gemini-3.8-flash/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-fable-5-1/2026-10-25T07:41:47.868693+00:00https://pombench.com/results/claude-fable-5-1/poster.pngClaude Fable 5.1 coding benchmark: PomBench Pomeranian animationClaude Fable 5.1 coding test: watch the animation it coded. 120,293 output tokens, known API cost $6.1168. Compare Claude Fable 5.1 vs Claude Opus 5.5.https://pombench.com/results/claude-fable-5-1/animation.mp4122026-10-25T07:41:47.868693+00:00yeshttps://pombench.com/animations/glm-5-3/2026-10-25T07:41:47.868693+00:00https://pombench.com/results/fw-glm-5-3/poster.pngGLM 5.3 coding benchmark: PomBench Pomeranian animationGLM 5.3 coding test: watch the animation it coded. 159,201 output tokens, known API cost $0.7053. Compare GLM 5.3 vs MAI-Thinking-1.https://pombench.com/results/fw-glm-5-3/animation.mp4122026-10-25T07:41:47.868693+00:00yeshttps://pombench.com/animations/mai-thinking-1/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/mai-thinking-1/poster.pngMAI-Thinking-1 coding benchmark: PomBench Pomeranian animationMAI-Thinking-1 coding test: watch the animation it coded. 11,089 output tokens, known API cost $0.0928. Compare MAI-Thinking-1 vs Claude Opus 5.https://pombench.com/results/mai-thinking-1/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-opus-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-opus-5/poster.pngClaude Opus 5 coding benchmark: PomBench Pomeranian animationClaude Opus 5 coding test: watch the animation it coded. 57,376 output tokens, known API cost $1.4689. Compare Claude Opus 5 vs Claude Sonnet 5.https://pombench.com/results/claude-opus-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gemini-3-5-flash-lite/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gemini-3.5-flash-lite/poster.pngGemini 3.5 Flash-Lite coding benchmark: PomBench Pomeranian animationGemini 3.5 Flash-Lite coding test: watch the animation it coded. 4,134 output tokens, known API cost $0.0110. Compare Gemini 3.5 Flash-Lite vs Gemini 3.8 Flash.https://pombench.com/results/gemini-3.5-flash-lite/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/kimi-k3/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/fw-kimi-k3/poster.pngKimi K3 coding benchmark: PomBench Pomeranian animationKimi K3 coding test: watch the animation it coded. 22,590 output tokens, known API cost $0.3452. Compare Kimi K3 vs Kimi K3.1 Pro.https://pombench.com/results/fw-kimi-k3/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-6-luna/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-6-luna/poster.pngGPT-5.6 Luna coding benchmark: PomBench Pomeranian animationGPT-5.6 Luna coding test: watch the animation it coded. 2,721 output tokens, known API cost $0.0038. Compare GPT-5.6 Luna vs GPT-5.6 Sol.https://pombench.com/results/gpt-5-6-luna/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-6-sol/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-6-sol/poster.pngGPT-5.6 Sol coding benchmark: PomBench Pomeranian animationGPT-5.6 Sol coding test: watch the animation it coded. 6,583 output tokens, known API cost $0.1418. Compare GPT-5.6 Sol vs GPT-5.6 Luna.https://pombench.com/results/gpt-5-6-sol/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-6-terra/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-6-terra/poster.pngGPT-5.6 Terra coding benchmark: PomBench Pomeranian animationGPT-5.6 Terra coding test: watch the animation it coded. 8,121 output tokens, known API cost $0.1183. Compare GPT-5.6 Terra vs GPT-5.6 Luna.https://pombench.com/results/gpt-5-6-terra/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-sonnet-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-sonnet-5/poster.pngClaude Sonnet 5 coding benchmark: PomBench Pomeranian animationClaude Sonnet 5 coding test: watch the animation it coded. 14,803 output tokens, known API cost $0.1547. Compare Claude Sonnet 5 vs Claude Opus 5.https://pombench.com/results/claude-sonnet-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-opus-4-8/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-opus-4-8/poster.pngClaude Opus 4.8 coding benchmark: PomBench Pomeranian animationClaude Opus 4.8 coding test: watch the animation it coded. 16,398 output tokens, known API cost $0.4265. Compare Claude Opus 4.8 vs Claude Sonnet 5.https://pombench.com/results/claude-opus-4-8/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/mistral-medium-3-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/mistral-medium-3-5/poster.pngMistral Medium 3.5 coding benchmark: PomBench Pomeranian animationMistral Medium 3.5 coding test: watch the animation it coded. 3,499 output tokens, known API cost $0.0294. Compare Mistral Medium 3.5 vs Mistral Large 3.https://pombench.com/results/mistral-medium-3-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/deepseek-v4-pro/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/deepseek-v4-pro/poster.pngDeepSeek V4 Pro coding benchmark: PomBench Pomeranian animationDeepSeek V4 Pro coding test: watch the animation it coded. 5,244 output tokens, verified price unavailable. Compare DeepSeek V4 Pro vs DeepSeek V4.1 Flash.https://pombench.com/results/deepseek-v4-pro/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-5/poster.pngGPT-5.5 coding benchmark: PomBench Pomeranian animationGPT-5.5 coding test: watch the animation it coded. 3,844 output tokens, known API cost $0.1255. Compare GPT-5.5 vs GPT-5.4 Mini.https://pombench.com/results/gpt-5-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-4-mini/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-4-mini/poster.pngGPT-5.4 Mini coding benchmark: PomBench Pomeranian animationGPT-5.4 Mini coding test: watch the animation it coded. 4,460 output tokens, known API cost $0.0216. Compare GPT-5.4 Mini vs GPT-5.4 Nano.https://pombench.com/results/gpt-5-4-mini/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-4-nano/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-4-nano/poster.pngGPT-5.4 Nano coding benchmark: PomBench Pomeranian animationGPT-5.4 Nano coding test: watch the animation it coded. 20,425 output tokens, known API cost $0.0284. Compare GPT-5.4 Nano vs GPT-5.4 Mini.https://pombench.com/results/gpt-5-4-nano/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-4/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-4/poster.pngGPT-5.4 coding benchmark: PomBench Pomeranian animationGPT-5.4 coding test: watch the animation it coded. 16,200 output tokens, known API cost $0.2714. Compare GPT-5.4 vs GPT-5.3 Codex.https://pombench.com/results/gpt-5-4/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-3-codex/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-3-codex/poster.pngGPT-5.3 Codex coding benchmark: PomBench Pomeranian animationGPT-5.3 Codex coding test: watch the animation it coded. 7,038 output tokens, known API cost $0.1021. Compare GPT-5.3 Codex vs GPT-5.4.https://pombench.com/results/gpt-5-3-codex/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gemini-3-1-pro-preview/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gemini-3.1-pro-preview/poster.pngGemini 3.1 Pro Preview coding benchmark: PomBench Pomeranian animationGemini 3.1 Pro Preview coding test: watch the animation it coded. 1,920 tokens, known API cost $0.0273. Compare Gemini 3.1 Pro Preview vs Gemini 3.5 Flash-Lite.https://pombench.com/results/gemini-3.1-pro-preview/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/mistral-large-3/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/mistral-large-3/poster.pngMistral Large 3 coding benchmark: PomBench Pomeranian animationMistral Large 3 coding test: watch the animation it coded. 5,448 output tokens, known API cost $0.0092. Compare Mistral Large 3 vs Mistral Medium 3.5.https://pombench.com/results/mistral-large-3/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/claude-haiku-4-5/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/claude-haiku-4-5/poster.pngClaude Haiku 4.5 coding benchmark: PomBench Pomeranian animationClaude Haiku 4.5 coding test: watch the animation it coded. 7,233 output tokens, known API cost $0.0384. Compare Claude Haiku 4.5 vs Claude Opus 4.8.https://pombench.com/results/claude-haiku-4-5/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-mini/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-mini/poster.pngGPT-5 Mini coding benchmark: PomBench Pomeranian animationGPT-5 Mini coding test: watch the animation it coded. 8,832 output tokens, known API cost $0.0182. Compare GPT-5 Mini vs GPT-5 Nano.https://pombench.com/results/gpt-5-mini/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-5-nano/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-5-nano/poster.pngGPT-5 Nano coding benchmark: PomBench Pomeranian animationGPT-5 Nano coding test: watch the animation it coded. 5,751 output tokens, known API cost $0.0024. Compare GPT-5 Nano vs GPT-5 Mini.https://pombench.com/results/gpt-5-nano/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-oss-120b/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-oss-120b/poster.pngGPT-OSS 120B coding benchmark: PomBench Pomeranian animationGPT-OSS 120B coding test: watch the animation it coded. 2,223 output tokens, known API cost $0.0016. Compare GPT-OSS 120B vs GPT-5 Mini.https://pombench.com/results/gpt-oss-120b/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-4-1-mini/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-4-1-mini/poster.pngGPT-4.1 Mini coding benchmark: PomBench Pomeranian animationGPT-4.1 Mini coding test: watch the animation it coded. 13,811 output tokens, known API cost $0.0229. Compare GPT-4.1 Mini vs GPT-4.1 Nano.https://pombench.com/results/gpt-4-1-mini/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-4-1-nano/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-4-1-nano/poster.pngGPT-4.1 Nano coding benchmark: PomBench Pomeranian animationGPT-4.1 Nano coding test: watch the animation it coded. 2,521 output tokens, known API cost $0.0012. Compare GPT-4.1 Nano vs GPT-4.1 Mini.https://pombench.com/results/gpt-4-1-nano/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/llama-4-maverick/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/llama-4-maverick-17b-128e-instruct-fp8/poster.pngLlama 4 Maverick coding benchmark: PomBench Pomeranian animationLlama 4 Maverick coding test: watch the animation it coded. 763 output tokens, known API cost $0.0013. Compare Llama 4 Maverick vs Llama 4 Scout.https://pombench.com/results/llama-4-maverick-17b-128e-instruct-fp8/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/llama-4-scout/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/llama-4-scout-17b-16e-instruct/poster.pngLlama 4 Scout coding benchmark: PomBench Pomeranian animationLlama 4 Scout coding test: watch the animation it coded. 696 output tokens, known API cost $0.0008. Compare Llama 4 Scout vs Llama 4 Maverick.https://pombench.com/results/llama-4-scout-17b-16e-instruct/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/codestral-2501/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/codestral-2501/poster.pngCodestral 2501 coding benchmark: PomBench Pomeranian animationCodestral 2501 coding test: watch the animation it coded. 1,440 output tokens, known API cost $0.0019. Compare Codestral 2501 vs Mistral Large 3.https://pombench.com/results/codestral-2501/animation.mp4122026-10-24T17:33:46.803982+00:00yeshttps://pombench.com/animations/gpt-4o-mini/2026-10-24T17:33:46.803982+00:00https://pombench.com/results/gpt-4o-mini/poster.pngGPT-4o Mini coding benchmark: PomBench Pomeranian animationGPT-4o Mini coding test: watch the animation it coded. 1,259 output tokens, known API cost $0.0012. Compare GPT-4o Mini vs GPT-4.1 Mini.https://pombench.com/results/gpt-4o-mini/animation.mp4122026-10-24T17:33:46.803982+00:00yes