# Compare finance AI models Two models on every benchmark where both have a score, with the source of each number. Pairs with at least two shared benchmarks have a page. ## Comparison pages - Claude Fable 5 vs Muse Spark 1.1: https://benchmarks.finance/compare/claude-fable-5-vs-muse-spark-1-1/ - Claude Fable 5.1 vs Claude Opus 5.5: https://benchmarks.finance/compare/claude-fable-5-1-vs-claude-opus-5-5/ - Claude Fable 5.1 vs Claude Sonnet 5.5: https://benchmarks.finance/compare/claude-fable-5-1-vs-claude-sonnet-5-5/ - Claude Fable 5.1 vs Gemini 4 Argon: https://benchmarks.finance/compare/claude-fable-5-1-vs-gemini-4-argon/ - Claude Fable 5.1 vs Gemini 4 Carbon: https://benchmarks.finance/compare/claude-fable-5-1-vs-gemini-4-carbon/ - Claude Fable 5.1 vs Wonder Full: https://benchmarks.finance/compare/claude-fable-5-1-vs-wonder-full/ - Claude Opus 4 vs Claude Opus 4.1: https://benchmarks.finance/compare/claude-opus-4-vs-claude-opus-4-1/ - Claude Opus 4 vs Claude Sonnet 4: https://benchmarks.finance/compare/claude-opus-4-vs-claude-sonnet-4/ - Claude Opus 4 vs GPT-4.1: https://benchmarks.finance/compare/claude-opus-4-vs-gpt-4-1/ - Claude Opus 4 vs gpt-5: https://benchmarks.finance/compare/claude-opus-4-vs-gpt-5/ - Claude Opus 4 vs GPT-o3: https://benchmarks.finance/compare/claude-opus-4-vs-gpt-o3/ - Claude Opus 4.1 vs DeepSeek V3.1: https://benchmarks.finance/compare/claude-opus-4-1-vs-deepseek-v3-1/ - Claude Opus 4.1 vs GPT-4.1: https://benchmarks.finance/compare/claude-opus-4-1-vs-gpt-4-1/ - Claude Opus 4.1 vs gpt-5: https://benchmarks.finance/compare/claude-opus-4-1-vs-gpt-5/ - Claude Opus 4.1 vs GPT-o3: https://benchmarks.finance/compare/claude-opus-4-1-vs-gpt-o3/ - Claude Opus 4.1 vs grok-4: https://benchmarks.finance/compare/claude-opus-4-1-vs-grok-4/ - Claude Opus 5.5 vs Claude Sonnet 5.5: https://benchmarks.finance/compare/claude-opus-5-5-vs-claude-sonnet-5-5/ - Claude Opus 5.5 vs DeepSeek V4.1 Flash 1017: https://benchmarks.finance/compare/claude-opus-5-5-vs-deepseek-v4-1-flash-1017/ - Claude Opus 5.5 vs Gemini 3.8 Flash: https://benchmarks.finance/compare/claude-opus-5-5-vs-gemini-3-8-flash/ - Claude Opus 5.5 vs Gemini 4 Argon: https://benchmarks.finance/compare/claude-opus-5-5-vs-gemini-4-argon/ - Claude Opus 5.5 vs Gemini 4 Carbon: https://benchmarks.finance/compare/claude-opus-5-5-vs-gemini-4-carbon/ - Claude Opus 5.5 vs GLM 5.3: https://benchmarks.finance/compare/claude-opus-5-5-vs-glm-5-3/ - Claude Opus 5.5 vs Numa 1: https://benchmarks.finance/compare/claude-opus-5-5-vs-numa-1/ - Claude Opus 5.5 vs Qwen 3.8 Max 0902: https://benchmarks.finance/compare/claude-opus-5-5-vs-qwen-3-8-max-0902/ - Claude Opus 5.5 vs Wonder: https://benchmarks.finance/compare/claude-opus-5-5-vs-wonder/ - Claude Opus 5.5 vs Wonder Full: https://benchmarks.finance/compare/claude-opus-5-5-vs-wonder-full/ - Claude Sonnet 4 vs Gemini 2.5 Flash: https://benchmarks.finance/compare/claude-sonnet-4-vs-gemini-2-5-flash/ - Claude Sonnet 4 vs Gemini 2.5 Pro: https://benchmarks.finance/compare/claude-sonnet-4-vs-gemini-2-5-pro/ - Claude Sonnet 4 vs GPT-4.1: https://benchmarks.finance/compare/claude-sonnet-4-vs-gpt-4-1/ - Claude Sonnet 5.5 vs DeepSeek V4.1 Flash 1017: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-deepseek-v4-1-flash-1017/ - Claude Sonnet 5.5 vs Gemini 3.8 Flash: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-gemini-3-8-flash/ - Claude Sonnet 5.5 vs Gemini 4 Argon: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-gemini-4-argon/ - Claude Sonnet 5.5 vs Gemini 4 Carbon: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-gemini-4-carbon/ - Claude Sonnet 5.5 vs GLM 5.3: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-glm-5-3/ - Claude Sonnet 5.5 vs Qwen 3.8 Max 0902: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-qwen-3-8-max-0902/ - Claude Sonnet 5.5 vs Wonder: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-wonder/ - Claude Sonnet 5.5 vs Wonder Full: https://benchmarks.finance/compare/claude-sonnet-5-5-vs-wonder-full/ - claude-sonnet-4.5 vs grok-4: https://benchmarks.finance/compare/claude-sonnet-4-5-vs-grok-4/ - DeepSeek V3.1 vs gpt-5: https://benchmarks.finance/compare/deepseek-v3-1-vs-gpt-5/ - DeepSeek V4.1 Flash 1017 vs Gemini 4 Argon: https://benchmarks.finance/compare/deepseek-v4-1-flash-1017-vs-gemini-4-argon/ - DeepSeek V4.1 Flash 1017 vs Gemini 4 Carbon: https://benchmarks.finance/compare/deepseek-v4-1-flash-1017-vs-gemini-4-carbon/ - DeepSeek V4.1 Flash 1017 vs Qwen 3.8 Max 0902: https://benchmarks.finance/compare/deepseek-v4-1-flash-1017-vs-qwen-3-8-max-0902/ - DeepSeek V4.1 Flash 1017 vs Wonder Full: https://benchmarks.finance/compare/deepseek-v4-1-flash-1017-vs-wonder-full/ - Fable 5.1 vs Muse Spark 1.3: https://benchmarks.finance/compare/fable-5-1-vs-muse-spark-1-3/ - Fable 5.1 vs Muse Wonder 1.0: https://benchmarks.finance/compare/fable-5-1-vs-muse-wonder-1-0/ - Gemini vs OpenAI: https://benchmarks.finance/compare/gemini-vs-openai/ - Gemini vs Perplexity: https://benchmarks.finance/compare/gemini-vs-perplexity/ - Gemini 2.5 Flash vs Gemini 2.5 Pro: https://benchmarks.finance/compare/gemini-2-5-flash-vs-gemini-2-5-pro/ - Gemini 2.5 Flash vs GPT-4.1: https://benchmarks.finance/compare/gemini-2-5-flash-vs-gpt-4-1/ - Gemini 2.5 Flash vs GPT-4.1-mini: https://benchmarks.finance/compare/gemini-2-5-flash-vs-gpt-4-1-mini/ - Gemini 2.5 Flash vs gpt-5: https://benchmarks.finance/compare/gemini-2-5-flash-vs-gpt-5/ - Gemini 2.5 Flash vs Llama-3.1-8B: https://benchmarks.finance/compare/gemini-2-5-flash-vs-llama-3-1-8b/ - Gemini 2.5 Flash vs o4-mini: https://benchmarks.finance/compare/gemini-2-5-flash-vs-o4-mini/ - Gemini 2.5 Pro vs gpt-5: https://benchmarks.finance/compare/gemini-2-5-pro-vs-gpt-5/ - Gemini 2.5 Pro vs grok-4: https://benchmarks.finance/compare/gemini-2-5-pro-vs-grok-4/ - Gemini 2.5 Pro vs Llama-3.1-8B: https://benchmarks.finance/compare/gemini-2-5-pro-vs-llama-3-1-8b/ - Gemini 3.8 Flash vs Gemini 4 Argon: https://benchmarks.finance/compare/gemini-3-8-flash-vs-gemini-4-argon/ - Gemini 3.8 Flash vs Gemini 4 Carbon: https://benchmarks.finance/compare/gemini-3-8-flash-vs-gemini-4-carbon/ - Gemini 3.8 Flash vs GLM 5.3: https://benchmarks.finance/compare/gemini-3-8-flash-vs-glm-5-3/ - Gemini 3.8 Flash vs Wonder: https://benchmarks.finance/compare/gemini-3-8-flash-vs-wonder/ - Gemini 3.8 Flash vs Wonder Full: https://benchmarks.finance/compare/gemini-3-8-flash-vs-wonder-full/ - Gemini 4 Argon vs Gemini 4 Carbon: https://benchmarks.finance/compare/gemini-4-argon-vs-gemini-4-carbon/ - Gemini 4 Argon vs GLM 5.3: https://benchmarks.finance/compare/gemini-4-argon-vs-glm-5-3/ - Gemini 4 Argon vs GPT-6 Astra: https://benchmarks.finance/compare/gemini-4-argon-vs-gpt-6-astra/ - Gemini 4 Argon vs Qwen 3.8 Max 0902: https://benchmarks.finance/compare/gemini-4-argon-vs-qwen-3-8-max-0902/ - Gemini 4 Argon vs Wonder: https://benchmarks.finance/compare/gemini-4-argon-vs-wonder/ - Gemini 4 Argon vs Wonder Full: https://benchmarks.finance/compare/gemini-4-argon-vs-wonder-full/ - Gemini 4 Carbon vs GLM 5.3: https://benchmarks.finance/compare/gemini-4-carbon-vs-glm-5-3/ - Gemini 4 Carbon vs GPT-6 Astra: https://benchmarks.finance/compare/gemini-4-carbon-vs-gpt-6-astra/ - Gemini 4 Carbon vs Qwen 3.8 Max 0902: https://benchmarks.finance/compare/gemini-4-carbon-vs-qwen-3-8-max-0902/ - Gemini 4 Carbon vs Wonder: https://benchmarks.finance/compare/gemini-4-carbon-vs-wonder/ - Gemini 4 Carbon vs Wonder Full: https://benchmarks.finance/compare/gemini-4-carbon-vs-wonder-full/ - gemini-3.1-pro vs GPT 5.5: https://benchmarks.finance/compare/gemini-3-1-pro-vs-gpt-5-5/ - GLM 5.3 vs Wonder: https://benchmarks.finance/compare/glm-5-3-vs-wonder/ - GLM 5.3 vs Wonder Full: https://benchmarks.finance/compare/glm-5-3-vs-wonder-full/ - GLM-5.1 vs Kimi K2.6: https://benchmarks.finance/compare/glm-5-1-vs-kimi-k2-6/ - GLM-5.1 vs Qwen3.6-Plus: https://benchmarks.finance/compare/glm-5-1-vs-qwen3-6-plus/ - GPT-4.1 vs GPT-4.1-mini: https://benchmarks.finance/compare/gpt-4-1-vs-gpt-4-1-mini/ - GPT-4.1 vs gpt-5: https://benchmarks.finance/compare/gpt-4-1-vs-gpt-5/ - GPT-4.1 vs GPT-o3: https://benchmarks.finance/compare/gpt-4-1-vs-gpt-o3/ - GPT-4o vs Llama-3.1-70B: https://benchmarks.finance/compare/gpt-4o-vs-llama-3-1-70b/ - GPT-4o vs Llama-3.3-70B: https://benchmarks.finance/compare/gpt-4o-vs-llama-3-3-70b/ - GPT-4o vs Qwen2.5-72B-Instruct: https://benchmarks.finance/compare/gpt-4o-vs-qwen2-5-72b-instruct/ - GPT-4o vs Qwen3-32B: https://benchmarks.finance/compare/gpt-4o-vs-qwen3-32b/ - gpt-5 vs GPT-o3: https://benchmarks.finance/compare/gpt-5-vs-gpt-o3/ - gpt-5 vs grok-4: https://benchmarks.finance/compare/gpt-5-vs-grok-4/ - Kimi K2.6 vs Qwen3.6-Plus: https://benchmarks.finance/compare/kimi-k2-6-vs-qwen3-6-plus/ - Muse Spark 1.3 vs Muse Wonder 1.0: https://benchmarks.finance/compare/muse-spark-1-3-vs-muse-wonder-1-0/ - OpenAI vs Perplexity: https://benchmarks.finance/compare/openai-vs-perplexity/ - Qwen 3.8 Max 0902 vs Wonder Full: https://benchmarks.finance/compare/qwen-3-8-max-0902-vs-wonder-full/ - Wonder vs Wonder Full: https://benchmarks.finance/compare/wonder-vs-wonder-full/ ## Models (230) - AutoGLM (Zhipu AI): scored on 1 benchmark - Cashcat Pro: scored on 1 benchmark - ChatGPT-o3 (OpenAI): scored on 1 benchmark - ChatGPT-o4-mini (OpenAI): scored on 1 benchmark - Claude Fable 5 (Anthropic): scored on 2 benchmarks - Claude Fable 5 · Finance Agent v2 (Anthropic): scored on 1 benchmark - Claude Fable 5.1 (Anthropic): scored on 2 benchmarks - Claude Fable 5.1 · Finance Agent v2 (Anthropic): scored on 1 benchmark - Claude Fable 5.1 (Max, Default Fallback) (Anthropic): scored on 1 benchmark - Claude Haiku 5.5 (Anthropic): scored on 1 benchmark - Claude Opus 4 (Anthropic): scored on 3 benchmarks - Claude Opus 4.1 (Anthropic): scored on 3 benchmarks - Claude Opus 5 (Anthropic): scored on 2 benchmarks - Claude Opus 5.5 (Anthropic): scored on 5 benchmarks - Claude Opus 5.5 · Finance Agent v2 (Anthropic): scored on 1 benchmark - Claude Sonnet 4 (Anthropic): scored on 3 benchmarks - Claude Sonnet 5.5 (Anthropic): scored on 4 benchmarks - Claude Sonnet 5.5 (Max, Default Fallback) (Anthropic): scored on 1 benchmark - Claude-3-5-sonnet-20241022 (Anthropic): scored on 1 benchmark - Claude-3.7-Sonnet (Anthropic): scored on 1 benchmark - Claude-4-Sonnet (Anthropic): scored on 1 benchmark - Claude-haiku-3 (Anthropic): scored on 1 benchmark - claude-opus-4-6 (Non-Thinking) (Anthropic): scored on 1 benchmark - claude-opus-4-7 (Anthropic): scored on 1 benchmark - claude-opus-4.5 (Anthropic): scored on 1 benchmark - Claude-Sonnet-3.7 (Anthropic): scored on 1 benchmark - claude-sonnet-4.5 (Anthropic): scored on 3 benchmarks - Claude2 (Anthropic): scored on 1 benchmark - command-a (Cohere): scored on 1 benchmark - d1: scored on 1 benchmark - d1-ultra: scored on 1 benchmark - DB-2.0-Lite: scored on 1 benchmark - DB-2.0-Pro: scored on 1 benchmark - Decider V1.1 27B: scored on 1 benchmark - Decider V1.2: scored on 1 benchmark - DeepFundAgent / GPT-4o: scored on 1 benchmark - DeepFundAgent / Vote: scored on 1 benchmark - DeepSeek V3.1 (DeepSeek): scored on 4 benchmarks - DeepSeek V4.1 Flash (DeepSeek): scored on 1 benchmark - DeepSeek V4.1 Flash 1017 (DeepSeek): scored on 2 benchmarks - DeepSeek-67B-Chat (DeepSeek): scored on 1 benchmark - DeepSeek-R1 (DeepSeek): scored on 2 benchmarks - DeepSeek-R1 (671B) (DeepSeek): scored on 1 benchmark - DeepSeek-V2-Lite (15.7B) (DeepSeek): scored on 1 benchmark - DeepSeek-V3 (DeepSeek): scored on 2 benchmarks - DeepSeek-V3 (671B) (DeepSeek): scored on 1 benchmark - deepseek-v3.2 (DeepSeek): scored on 3 benchmarks - deepseek-v4-pro (DeepSeek): scored on 1 benchmark - DianJin-R1: scored on 1 benchmark - DouBao (ByteDance): scored on 1 benchmark - doubao-seed-2.0 (ByteDance): scored on 1 benchmark - DouBao-Thinking (ByteDance): scored on 1 benchmark - Drex Max: scored on 1 benchmark - Drex v1.5: scored on 1 benchmark - DS-V4-Flash (DeepSeek): scored on 1 benchmark - DS-V4-Pro (DeepSeek): scored on 1 benchmark - ERNIE-X1 (Baidu): scored on 1 benchmark - EXAONE-4.0-32B (LG): scored on 1 benchmark - Fable 5.1 (Anthropic): scored on 2 benchmarks - Fin-R1: scored on 1 benchmark - FinAgentTest: scored on 1 benchmark - Gemini (Google): scored on 2 benchmarks - Gemini 2.5 Flash (Google): scored on 5 benchmarks - Gemini 2.5 Pro (Google): scored on 5 benchmarks - Gemini 3 Pro (Google): scored on 1 benchmark - Gemini 3 Pro Deep Research (Google): scored on 1 benchmark - Gemini 3.0 Pro (Google): scored on 1 benchmark - Gemini 3.7 Flash (High) (Google): scored on 1 benchmark - Gemini 3.8 Flash (Google): scored on 3 benchmarks - Gemini 3.8 Flash · Finance Agent v2 (Google): scored on 1 benchmark - Gemini 4 Argon (Google): scored on 5 benchmarks - Gemini 4 Carbon (Google): scored on 5 benchmarks - Gemini-2.0-Flash (Google): scored on 1 benchmark - Gemini-2.5-flash-lite (Google): scored on 1 benchmark - Gemini-3-Flash (Google): scored on 1 benchmark - gemini-3-pro-preview (Google): scored on 1 benchmark - gemini-3.1-pro (Google): scored on 2 benchmarks - Gemini2.5-pro (Google): scored on 1 benchmark - Gemini2.5-pro (Google Search) (Google): scored on 1 benchmark - Gemma-3-27B (Google): scored on 1 benchmark - Gemma-3-4B (Google): scored on 1 benchmark - Genspark*: scored on 1 benchmark - GLM 5.3 (Zhipu AI): scored on 2 benchmarks - GLM-4 (Zhipu AI): scored on 1 benchmark - GLM-4.5 (Zhipu AI): scored on 1 benchmark - GLM-5.1 (Zhipu AI): scored on 3 benchmarks - GLM-5.2 (Zhipu AI): scored on 1 benchmark - GPT 5.1 Pro (OpenAI): scored on 1 benchmark - GPT 5.5 (OpenAI): scored on 3 benchmarks - GPT 5.6 Sol · Finance Agent v2 (OpenAI): scored on 1 benchmark - GPT-4 (OpenAI): scored on 1 benchmark - GPT-4-Turbo (OpenAI): scored on 1 benchmark - GPT-4.1 (OpenAI): scored on 4 benchmarks - GPT-4.1-mini (OpenAI): scored on 2 benchmarks - GPT-4.1-nano (OpenAI): scored on 1 benchmark - GPT-4o (OpenAI): scored on 6 benchmarks - gpt-5 (OpenAI): scored on 7 benchmarks - gpt-5-pro (OpenAI): scored on 1 benchmark - GPT-5-Thinking (OpenAI): scored on 1 benchmark - GPT-5.1 (OpenAI): scored on 1 benchmark - gpt-5.1-codex-max (OpenAI): scored on 1 benchmark - gpt-5.2 (OpenAI): scored on 1 benchmark - GPT-5.4 (OpenAI): scored on 1 benchmark - gpt-5.6-sol (max) (OpenAI): scored on 1 benchmark - GPT-6 Astra (OpenAI): scored on 2 benchmarks - GPT-6.1 Sol (OpenAI): scored on 1 benchmark - GPT-6.1 Terra (OpenAI): scored on 1 benchmark - GPT-o1-preview (OpenAI): scored on 1 benchmark - GPT-o3 (OpenAI): scored on 2 benchmarks - GPT-OSS 120B (OpenAI): scored on 2 benchmarks - Grok (xAI): scored on 1 benchmark - Grok 4 Fast Reasoning (xAI): scored on 1 benchmark - Grok 4.20 (xAI): scored on 1 benchmark - Grok 4.3 (xAI): scored on 1 benchmark - Grok-3 (xAI): scored on 1 benchmark - Grok-3 Mini Low Effort (xAI): scored on 1 benchmark - grok-4 (xAI): scored on 5 benchmarks - Grok-4.1-Fast (xAI): scored on 1 benchmark - HunYuan-T1-Thinking (Tencent): scored on 1 benchmark - HY3-Preview (Tencent): scored on 1 benchmark - Inkling: scored on 1 benchmark - Inkling Small: scored on 1 benchmark - InternLM3: scored on 1 benchmark - InvestorAgent / Claude-3.5-haiku: scored on 1 benchmark - InvestorAgent / Claude-sonnet-4: scored on 1 benchmark - InvestorAgent / Gemini-2.0-flash: scored on 1 benchmark - InvestorAgent / GPT-4.1: scored on 1 benchmark - InvestorAgent / GPT-4o: scored on 1 benchmark - InvestorAgent / Vote: scored on 1 benchmark - Jev 1.13.0: scored on 1 benchmark - Jev 1.14: scored on 1 benchmark - Kimi k2 (Moonshot AI): scored on 2 benchmarks - Kimi K2 Instruct (Moonshot AI): scored on 1 benchmark - Kimi K2.5 (Moonshot AI): scored on 1 benchmark - Kimi K2.6 (Moonshot AI): scored on 3 benchmarks - Kimi K3 (Moonshot AI): scored on 1 benchmark - Legacy Samaya System (Samaya AI): scored on 1 benchmark - Legacy Samaya System (high effort) (Samaya AI): scored on 1 benchmark - LLaMA-3 (Meta): scored on 1 benchmark - Llama-3.1-70B (Meta): scored on 2 benchmarks - Llama-3.1-70B-Instruct (Meta): scored on 1 benchmark - Llama-3.1-8B (Meta): scored on 2 benchmarks - Llama-3.1-8B-Instruct (Meta): scored on 1 benchmark - llama-3.1-nemotron-ultra (Meta): scored on 1 benchmark - Llama-3.2-1B (Meta): scored on 1 benchmark - Llama-3.2-3B (Meta): scored on 1 benchmark - Llama-3.3-70B (Meta): scored on 2 benchmarks - Llama-3.3-70B-Instruct (Meta): scored on 1 benchmark - Llama-4-Maverick-17B-128E-Instruct-FP8 (Meta): scored on 1 benchmark - Llama-4-Scout-17B-16E (Meta): scored on 1 benchmark - Llama2 (Meta): scored on 1 benchmark - Llama4-Maverick (Meta): scored on 1 benchmark - Llama4-Scout (Meta): scored on 1 benchmark - Mercury Decide: scored on 1 benchmark - Microsoft-Decision-1 (Microsoft): scored on 1 benchmark - MiMo-2.5 Pro (Xiaomi): scored on 1 benchmark - MiMo-V2-Flash (Xiaomi): scored on 1 benchmark - MiniMax-M2 (MiniMax): scored on 1 benchmark - MiniMax-M2.5 (MiniMax): scored on 1 benchmark - minimax-m2.7 (MiniMax): scored on 1 benchmark - Minimax* (MiniMax): scored on 1 benchmark - Mistral (Mistral AI): scored on 1 benchmark - Mistral-8x22B (Mistral AI): scored on 1 benchmark - Mistral-Small-24B (Mistral AI): scored on 1 benchmark - Muse Spark (Meta): scored on 1 benchmark - Muse Spark 1.1 (Meta): scored on 2 benchmarks - Muse Spark 1.2 (Meta): scored on 1 benchmark - Muse Spark 1.3 (Meta): scored on 2 benchmarks - Muse Spark 1.3 Max (Meta): scored on 1 benchmark - Muse Spark Open · Finance Agent v2 (Meta): scored on 1 benchmark - Muse Wonder 1.0 (Meta): scored on 2 benchmarks - Muse Wonder 1.0 · Finance Agent v2 (Meta): scored on 1 benchmark - Nemotron 3 Ultra (NVIDIA): scored on 1 benchmark - nova-premier-v1 (Amazon): scored on 1 benchmark - Numa 1 (Moneda): scored on 6 benchmarks - o1 (OpenAI): scored on 1 benchmark - o3-mini (OpenAI): scored on 1 benchmark - o4-mini (OpenAI): scored on 2 benchmarks - OpenAI (OpenAI): scored on 2 benchmarks - OpenAI GPT-5 (OpenAI): scored on 1 benchmark - OpenAI o3-deep-research (OpenAI): scored on 1 benchmark - OpenAI-O3 (OpenAI): scored on 1 benchmark - Opus 4.7 (Anthropic): scored on 1 benchmark - Opus 5 (Anthropic): scored on 1 benchmark - Opus 5.5 (Anthropic): scored on 1 benchmark - Perplexity (Perplexity): scored on 2 benchmarks - Perplexity Sonar Deep Research (Perplexity): scored on 1 benchmark - phi-4 (Microsoft): scored on 1 benchmark - Qwen 3.7 Max (Qwen): scored on 1 benchmark - Qwen 3.8 Max 0902 (Qwen): scored on 2 benchmarks - Qwen-2.5-Instruct-7B (Qwen): scored on 1 benchmark - Qwen-3-32B (Qwen): scored on 1 benchmark - Qwen2-Audio-7B (Qwen): scored on 1 benchmark - Qwen2-Audio-7B-Instruct (Qwen): scored on 1 benchmark - Qwen2.5 (Qwen): scored on 1 benchmark - Qwen2.5-32B (Qwen): scored on 1 benchmark - Qwen2.5-72B (Qwen): scored on 1 benchmark - Qwen2.5-72B-Instruct (Qwen): scored on 3 benchmarks - Qwen2.5-Omni-7B (Qwen): scored on 1 benchmark - Qwen2.5-VL-32B (Qwen): scored on 1 benchmark - Qwen2.5-VL-72B (Qwen): scored on 1 benchmark - Qwen3-14B (Qwen): scored on 1 benchmark - Qwen3-235B-A22B-2507 (Qwen): scored on 1 benchmark - Qwen3-235B-A22B-FP8 (Qwen): scored on 1 benchmark - Qwen3-235B-Ins (Qwen): scored on 1 benchmark - Qwen3-235B-Think (Qwen): scored on 1 benchmark - Qwen3-30B-Think (Qwen): scored on 1 benchmark - Qwen3-32B (Qwen): scored on 2 benchmarks - Qwen3-Coder (Qwen): scored on 1 benchmark - Qwen3-Max (Qwen): scored on 1 benchmark - Qwen3.6-35B-A3B (Qwen): scored on 1 benchmark - Qwen3.6-Plus (Qwen): scored on 2 benchmarks - Qwen3.7-Max (Qwen): scored on 1 benchmark - Reportify: scored on 1 benchmark - Samaya Sterling (Samaya AI): scored on 1 benchmark - Sonnet 4.6 (Anthropic): scored on 1 benchmark - Sonnet 5.5 (Anthropic): scored on 1 benchmark - step-3.5-flash (StepFun): scored on 1 benchmark - Tongyi Deep Research (Qwen): scored on 1 benchmark - TradeAgent / Gemini-2.0-flash: scored on 1 benchmark - TradeAgent / Vote: scored on 1 benchmark - Trinity-Large: scored on 1 benchmark - Whisper-V3 (OpenAI): scored on 1 benchmark - Wonder: scored on 3 benchmarks - Wonder Full: scored on 4 benchmarks - XuanYuan: scored on 1 benchmark - XuanYuan-Fin-X1-Preview: scored on 1 benchmark - Yi-1.5-34B-Chat: scored on 1 benchmark - YuanBao-DeepSeek-R1: scored on 1 benchmark - YuanBao-DeepSeek-V3: scored on 1 benchmark Source: https://benchmarks.finance/compare/ Created and maintained by Moneda.