https://benchscore.si/https://benchscore.si/leaderboard/https://benchscore.si/methodology/https://benchscore.si/models/https://benchscore.si/models/claude-3-5-sonnet-20240620-f85a9cf8/https://benchscore.si/models/claude-3-haiku-20240307-ddff2371/https://benchscore.si/models/claude-3-opus-20240229-3f1e86a6/https://benchscore.si/models/claude-3-sonnet-20240229-f3040325/https://benchscore.si/models/claude-fable-5-1-f8064a23/https://benchscore.si/models/claude-haiku-4-5-20251001-09d0ceca/https://benchscore.si/models/claude-opus-4-5-20251101-7c148407/https://benchscore.si/models/claude-opus-4-6-0b03295f/https://benchscore.si/models/claude-opus-4-7-b1171b42/https://benchscore.si/models/claude-opus-4-8-47a46a22/https://benchscore.si/models/claude-opus-5-5-005912be/https://benchscore.si/models/claude-opus-5-f9ef6eed/https://benchscore.si/models/claude-sonnet-4-5-20250929-efcf3085/https://benchscore.si/models/claude-sonnet-4-6-7d811269/https://benchscore.si/models/claude-sonnet-5-4b07d9a5/https://benchscore.si/models/claude-sonnet-5-5-c13e6668/https://benchscore.si/models/deepseek-v4-1-flash-eb1394ac/https://benchscore.si/models/deepseek-v4-flash-0731-52f67337/https://benchscore.si/models/deepseek-v4-pro-0813-16e962c0/https://benchscore.si/models/devstral-medium-2507-73340562/https://benchscore.si/models/devstral-small-2505-7e357a7a/https://benchscore.si/models/gemini-1-5-flash-api-0514-fe67da44/https://benchscore.si/models/gemini-1-5-pro-api-0514-9ae9f940/https://benchscore.si/models/gemini-2-5-flash-de40daba/https://benchscore.si/models/gemini-2-5-flash-lite-03696df5/https://benchscore.si/models/gemini-2-5-pro-6d734050/https://benchscore.si/models/gemini-3-1-pro-preview-edce75de/https://benchscore.si/models/gemini-3-5-flash-lite-37a58c16/https://benchscore.si/models/gemini-3-7-flash-4aa2768e/https://benchscore.si/models/gemini-3-8-flash-319034f3/https://benchscore.si/models/gemini-3-flash-preview-bb3981be/https://benchscore.si/models/glm-5-3-9691a990/https://benchscore.si/models/glm-5-3-flash-0d872417/https://benchscore.si/models/gpt-3-5-turbo-0125-554e3dab/https://benchscore.si/models/gpt-4-1-5c51a66b/https://benchscore.si/models/gpt-4-1-mini-13a647d4/https://benchscore.si/models/gpt-4-1-nano-bf2bf007/https://benchscore.si/models/gpt-4-0125-preview-f8b4f0f3/https://benchscore.si/models/gpt-4-turbo-2024-04-09-1a000e12/https://benchscore.si/models/gpt-4o-2024-05-13-373b2ee1/https://benchscore.si/models/gpt-4o-2024-08-06-494a14f4/https://benchscore.si/models/gpt-4o-2024-11-20-247c298f/https://benchscore.si/models/gpt-4o-a2a69af7/https://benchscore.si/models/gpt-4o-mini-8a434280/https://benchscore.si/models/gpt-5-2-131e2083/https://benchscore.si/models/gpt-5-4-2a7b79b0/https://benchscore.si/models/gpt-5-4-mini-d416b3a3/https://benchscore.si/models/gpt-5-4-nano-d4694a1a/https://benchscore.si/models/gpt-5-4-pro-a31d36a6/https://benchscore.si/models/gpt-5-5-ffc50c70/https://benchscore.si/models/gpt-5-6-luna-e33230db/https://benchscore.si/models/gpt-5-6-sol-419255f2/https://benchscore.si/models/gpt-5-6-terra-deda3dc0/https://benchscore.si/models/gpt-5-b0a9d642/https://benchscore.si/models/gpt-5-mini-f6a6fd96/https://benchscore.si/models/gpt-5-nano-6c132517/https://benchscore.si/models/gpt-6-1-sol-dedfefd5/https://benchscore.si/models/gpt-6-astra-576a599a/https://benchscore.si/models/gpt-6-luna-9a7e60cd/https://benchscore.si/models/gpt-6-sol-7388db16/https://benchscore.si/models/grok-4-6-44968622/https://benchscore.si/models/grok-4-7-459415a9/https://benchscore.si/models/kimi-k2-8-preview-ee733bdd/https://benchscore.si/models/kimi-k3-80a8bf70/https://benchscore.si/models/mimo-v2-6-pro-42f4aabe/https://benchscore.si/models/minimax-m3-1-flash-preview-7c55f68b/https://benchscore.si/models/minimax-m3-ac72b9b9/https://benchscore.si/models/mistral-large-2411-82cac7c2/https://benchscore.si/models/mistral-medium-2508-c07f8136/https://benchscore.si/models/mistral-medium-2604-7beb9f92/https://benchscore.si/models/mistral-small-2506-0185ad54/https://benchscore.si/models/mistral-small-2603-2391abd1/https://benchscore.si/models/muse-spark-1-3-b3eba54f/https://benchscore.si/models/o3-de2d91dc/https://benchscore.si/models/o3-mini-dfc32530/https://benchscore.si/models/o4-mini-9056e330/https://benchscore.si/models/qwen3-8-27b-66fc7c05/https://benchscore.si/models/qwen3-8-flash-next-9b17db7a/https://benchscore.si/models/qwen3-8-max-bc33b81a/https://benchscore.si/models/qwen3-8-max-prime-be40055d/https://benchscore.si/sources/https://benchscore.si/tasks/https://benchscore.si/tasks/code-budget/https://benchscore.si/tasks/tool-calling/https://benchscore.si/updates/