{"task":"math","generated_at":"2026-04-24","count":10,"items":[{"slug":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","id":"gpt-5.4-thinking","provider":"OpenAI","score":97,"score_basis":"benchmark.math","pricing":{"input":"$10.00 / 1M tokens","output":"$40.00 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":50,"model_type":"proprietary","markdown_url":"/content/models/gpt-5.4-thinking.md","html_url":"/models/gpt-5.4-thinking","api_url":"/api/v1/models/gpt-5.4-thinking.json","sha256":"40bd1ae425c863f5a20a5c11e5419f0f4f6d6f915e22a707e194f6b018c1f2cf"},{"slug":"kimi-k2.5","title":"Kimi K2.5","id":"kimi-k2.5","provider":"Moonshot AI","score":97,"score_basis":"benchmark.math","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)"},"free":true,"estimated_input_output_cost_per_1m":0,"model_type":"open-source","markdown_url":"/content/models/kimi-k2.5.md","html_url":"/models/kimi-k2.5","api_url":"/api/v1/models/kimi-k2.5.json","sha256":"ab881ce9ca6e96be96c32c086c7b32453d9d521fa73913418d93fa7acd5e1520"},{"slug":"gpt-5.4","title":"GPT-5.4","id":"gpt-5.4","provider":"OpenAI","score":95,"score_basis":"benchmark.math","pricing":{"input":"$5.00 / 1M tokens","output":"$15.00 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":20,"model_type":"proprietary","markdown_url":"/content/models/gpt-5.4.md","html_url":"/models/gpt-5.4","api_url":"/api/v1/models/gpt-5.4.json","sha256":"dae20b16e893dcd5b0f2baeb4f785195b83ba98a1b799126bceab3845e9d7d7e"},{"slug":"deepseek-r1","title":"DeepSeek R1","id":"deepseek-r1","provider":"DeepSeek","score":94,"score_basis":"benchmark.math","pricing":{"input":"$0.55 / 1M tokens","output":"$2.19 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":2.74,"model_type":"open-source","markdown_url":"/content/models/deepseek-r1.md","html_url":"/models/deepseek-r1","api_url":"/api/v1/models/deepseek-r1.json","sha256":"82337e0cad76f5697b684824360eb063620b86b838f2550c40857a2257cc90f2"},{"slug":"qwen-3.5","title":"Qwen 3.5 397B-A17B","id":"qwen-3.5","provider":"Alibaba","score":94,"score_basis":"benchmark.math","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)"},"free":true,"estimated_input_output_cost_per_1m":0,"model_type":"open-source","markdown_url":"/content/models/qwen-3.5.md","html_url":"/models/qwen-3.5","api_url":"/api/v1/models/qwen-3.5.json","sha256":"e6f1fe3693f685475bfb8c819995c27a29bee4321a03ed12249578b68fb6198f"},{"slug":"claude-opus-4.6","title":"Claude Opus 4.6","id":"claude-opus-4.6","provider":"Anthropic","score":93,"score_basis":"benchmark.math","pricing":{"input":"$5.00 / 1M tokens","output":"$25.00 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":30,"model_type":"proprietary","markdown_url":"/content/models/claude-opus-4.6.md","html_url":"/models/claude-opus-4.6","api_url":"/api/v1/models/claude-opus-4.6.json","sha256":"51a0a4c31212a32a86a8e6d0d5a3a7844bb7bcf4454e0237f9693476e284df48"},{"slug":"gemini-3.1-pro","title":"Gemini 3.1 Pro","id":"gemini-3.1-pro","provider":"Google","score":92,"score_basis":"benchmark.math","pricing":{"input":"$2.00 / 1M tokens","output":"$12.00 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":14,"model_type":"proprietary","markdown_url":"/content/models/gemini-3.1-pro.md","html_url":"/models/gemini-3.1-pro","api_url":"/api/v1/models/gemini-3.1-pro.json","sha256":"95504fb958957b344c2ed8ffcf4e5545aafb3eb285acf694668ec13cd38b7bfe"},{"slug":"nemotron-cascade-2","title":"Nemotron-Cascade 2","id":"nemotron-cascade-2","provider":"NVIDIA","score":92,"score_basis":"benchmark.math","pricing":{"input":"Free (open weights)","output":"Free (open weights)"},"free":true,"estimated_input_output_cost_per_1m":0,"model_type":"open-source","markdown_url":"/content/models/nemotron-cascade-2.md","html_url":"/models/nemotron-cascade-2","api_url":"/api/v1/models/nemotron-cascade-2.json","sha256":"e2169ac59e26102777a47d9984fd843bd6a7a7d460ac6de4c9cc8b3e67661f94"},{"slug":"qwen-3","title":"Qwen 3","id":"qwen-3","provider":"Alibaba","score":92,"score_basis":"benchmark.math","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)"},"free":true,"estimated_input_output_cost_per_1m":0,"model_type":"open-source","markdown_url":"/content/models/qwen-3.md","html_url":"/models/qwen-3","api_url":"/api/v1/models/qwen-3.json","sha256":"101bb63231ffecd8f44c24f0e7373fcab02cf3fb0e7c30b74225e3f3e106509b"},{"slug":"grok-4.1","title":"Grok 4.1","id":"grok-4.1","provider":"xAI","score":91,"score_basis":"benchmark.math","pricing":{"input":"$3.00 / 1M tokens","output":"$15.00 / 1M tokens"},"free":false,"estimated_input_output_cost_per_1m":18,"model_type":"proprietary","markdown_url":"/content/models/grok-4.1.md","html_url":"/models/grok-4.1","api_url":"/api/v1/models/grok-4.1.json","sha256":"efb07266f1333573c72d3df8eb5e5155bb143f0a9a1b14428f8264de48e9394c"}]}